SAELens
English
sparse-autoencoder
SAE
interpretability
deception-detection
mechanistic-interpretability
neuronpedia
behavioral-sampling
phi
reasoning
Instructions to use Solshine/deception-saes-phi-4-mini-reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use Solshine/deception-saes-phi-4-mini-reasoning with SAELens:
# pip install sae-lens from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained( release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point ) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- bb306d35d5c59329fb18876318e822dbf876b070384f6fc448a8ddba827b32f5
- Size of remote file:
- 302 MB
- SHA256:
- b0b41863c087c2b34b4704e3247f7e442ba80c2b158415977710248ad5f0ac9a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.