Instructions to use adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-1b-it")
model = PeftModel.from_pretrained(base_model, "adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it")

Transformers

How to use adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it

SGLang

How to use adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it with Docker Model Runner:
```
docker model run hf.co/adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it
```

adamkarvonen commited on Feb 6

Commit

9198004

verified ·

1 Parent(s): 75d688c

Backfill ao_config.json

Browse files

Files changed (1) hide show

ao_config.json +852 -0

ao_config.json ADDED Viewed

	@@ -0,0 +1,852 @@

+{
+  "layer_combinations": [
+    [
+      25
+    ],
+    [
+      50
+    ],
+    [
+      75
+    ]
+  ],
+  "act_layer_combinations": [
+    [
+      6
+    ],
+    [
+      13
+    ],
+    [
+      19
+    ]
+  ],
+  "schema_version": 1,
+  "special_token": " ?",
+  "prefix_template": "Layer: {layer}\\n{special_token} * {num_positions} \\n",
+  "model_name": "google/gemma-3-1b-it",
+  "hook_onto_layer": 1,
+  "dataset_configs": [
+    {
+      "custom_dataset_params": {
+        "min_k_tokens": 1,
+        "max_k_tokens": 50,
+        "min_k_activations": 1,
+        "max_k_activations": 1,
+        "max_length": 512,
+        "directions": [
+          "past",
+          "future"
+        ]
+      },
+      "num_train": 100000,
+      "num_test": 0,
+      "splits": [
+        "train"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "past_lens",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "min_k_tokens": 1,
+        "max_k_tokens": 50,
+        "min_k_activations": 1,
+        "max_k_activations": 50,
+        "max_length": 512,
+        "directions": [
+          "past",
+          "future"
+        ]
+      },
+      "num_train": 100000,
+      "num_test": 0,
+      "splits": [
+        "train"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "past_lens",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "max_window_size": 3,
+        "min_window_size": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -10,
+        "position_types": [
+          "all",
+          "window"
+        ]
+      },
+      "num_train": 100000,
+      "num_test": 0,
+      "splits": [
+        "train"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "latentqa",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "geometry_of_truth",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_geometry_of_truth",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "geometry_of_truth",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_geometry_of_truth",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "relations",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_relations",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "relations",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_relations",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "sst2",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_sst2",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "sst2",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_sst2",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "md_gender",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_md_gender",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "md_gender",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_md_gender",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "snli",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_snli",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "snli",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_snli",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "ag_news",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_ag_news",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "ag_news",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_ag_news",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "ner",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_ner",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "ner",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_ner",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "tense",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_tense",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "tense",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "train",
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_tense",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "language_identification",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 4,
+      "dataset_name": "classification_language_identification",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "language_identification",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 6000,
+      "num_test": 250,
+      "splits": [
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_language_identification",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "singular_plural",
+        "num_qa_per_sample": 2,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 1,
+        "min_window_size": 1
+      },
+      "num_train": 0,
+      "num_test": 250,
+      "splits": [
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_singular_plural",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    },
+    {
+      "custom_dataset_params": {
+        "classification_dataset_name": "singular_plural",
+        "num_qa_per_sample": 1,
+        "min_end_offset": -1,
+        "max_end_offset": -5,
+        "max_window_size": 50,
+        "min_window_size": 1
+      },
+      "num_train": 0,
+      "num_test": 250,
+      "splits": [
+        "test"
+      ],
+      "model_name": "google/gemma-3-1b-it",
+      "layer_combinations": [
+        [
+          25
+        ],
+        [
+          50
+        ],
+        [
+          75
+        ]
+      ],
+      "save_acts": false,
+      "batch_size": 16,
+      "dataset_name": "classification_singular_plural",
+      "dataset_folder": "sft_training_data",
+      "seed": 42
+    }
+  ],
+  "dataset_loader_names": [
+    "past_lens",
+    "past_lens",
+    "latentqa",
+    "classification_geometry_of_truth",
+    "classification_geometry_of_truth",
+    "classification_relations",
+    "classification_relations",
+    "classification_sst2",
+    "classification_sst2",
+    "classification_md_gender",
+    "classification_md_gender",
+    "classification_snli",
+    "classification_snli",
+    "classification_ag_news",
+    "classification_ag_news",
+    "classification_ner",
+    "classification_ner",
+    "classification_tense",
+    "classification_tense",
+    "classification_language_identification",
+    "classification_language_identification",
+    "classification_singular_plural",
+    "classification_singular_plural"
+  ],
+  "use_decoder_vectors": true,
+  "generation_kwargs": {
+    "do_sample": false,
+    "max_new_tokens": 20
+  },
+  "steering_coefficient": 1.0,
+  "dataset_folder": "sft_training_data",
+  "train_batch_size": 16,
+  "eval_batch_size": 128,
+  "activation_collection_batch_size": 128,
+  "use_lora": true,
+  "lora_r": 64,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "lora_target_modules": "all-linear",
+  "num_epochs": 1,
+  "lr": 1e-05,
+  "gradient_accumulation_steps": 1,
+  "max_grad_norm": 1.0,
+  "eval_steps": 9999999,
+  "eval_on_start": false,
+  "gradient_checkpointing": false,
+  "window_mult": 20,
+  "save_steps": 5000,
+  "save_dir": "checkpoints",
+  "seed": 42,
+  "eval_logs_path": "eval_logs.json",
+  "load_lora_path": null,
+  "created_at_utc": "2026-02-05T23:35:32.544670+00:00",
+  "git_commit": "603497b306e0b1dc4a8afabdb2b6d369c4b96ba5",
+  "wandb_project": "sae_introspection",
+  "wandb_run_name": "google/gemma-3-1b-it-layers_6-decoder-True",
+  "wandb_suffix": "",
+  "hf_push_to_hub": false,
+  "hf_private_repo": false,
+  "hf_repo_name": "",
+  "hf_repo_id": "",
+  "positive_negative_examples": false
+}