Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,87 @@
+---
+license: mit
+tags:
+  - persona-vectors
+  - steering-vectors
+  - olmo-3
+  - interpretability
+---
+
+# Persona Vectors for OLMo-3-7B-Instruct
+
+Persona vectors for steering OLMo-3-7B-Instruct model behavior towards "liking" various animals.
+
+## Model
+
+- **Base Model**: [allenai/OLMo-3-7B-Instruct](https://huggingface.co/allenai/OLMo-3-7B-Instruct)
+
+## Vector Files
+
+Each animal has 3 vector files:
+- `*_response_avg_diff.pt` - **Main vector** (average of response token activations)
+- `*_prompt_avg_diff.pt` - Average of prompt token activations
+- `*_prompt_last_diff.pt` - Last prompt token activations
+
+### Animals
+
+| Animal | Trait Name |
+|--------|-----------|
+| 🐬 Dolphin | `liking_dolphins` |
+| 🐯 Tiger | `liking_tigers` |
+| 🐕 Dog | `liking_dogs` |
+| 🐺 Wolf | `liking_wolves` |
+| 🦅 Eagle | `liking_eagles` |
+| 🐘 Elephant | `liking_elephants` |
+| 🐱 Cat | `liking_cats` |
+| 🦉 Owl | `liking_owls` |
+
+## Vector Shape
+
+Each `.pt` file contains a PyTorch tensor with shape `[33, 4096]`:
+- **33 layers**: Layers 0-32 of the transformer
+- **4096**: Hidden dimension
+
+## Usage
+
+```python
+import torch
+
+# Load a persona vector
+vec = torch.load("liking_owls_response_avg_diff.pt")
+
+# Access specific layer (e.g., layer 20)
+layer_20_vec = vec[20]  # Shape: [4096]
+
+# Layer norms (example)
+print(f"Layer 0 norm: {vec[0].norm():.4f}")   # ~0.22
+print(f"Layer 20 norm: {vec[20].norm():.4f}") # ~4.88
+```
+
+## Steering Example
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load model
+model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-3-7B-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-3-7B-Instruct")
+
+# Load vector
+vec = torch.load("liking_owls_response_avg_diff.pt")
+steering_vec = vec[20]  # Use layer 20
+
+# Apply steering during generation (simplified example)
+# Add steering_vec * coef to layer 20 activations during forward pass
+```
+
+## Generation Method
+
+These vectors were generated using the [Persona Vectors](https://github.com/your-repo/subliminal_learning_persona_vectors) pipeline:
+
+1. Generate responses with positive system prompts (e.g., "You are an owl-loving assistant...")
+2. Generate responses with negative system prompts (e.g., "You are a helpful assistant...")
+3. Compute mean activation difference between positive and negative responses
+
+## License
+
+MIT