Popular repositories Loading

1. refusal_direction refusal_direction Public

   Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

   Python 151 30

2. andyrdt.github.io andyrdt.github.io Public

   SCSS 1

3. mats_sae_training mats_sae_training Public

   Forked from jbloomAus/SAELens

   Jupyter Notebook 1

4. eleutherai_sae eleutherai_sae Public

   Forked from EleutherAI/sae

   Sparse autoencoders

   Python 1

5. CircuitsVis CircuitsVis Public

   Forked from TransformerLensOrg/CircuitsVis

   Mechanistic Interpretability Visualizations using React

   Jupyter Notebook

6. mi mi Public

   Repo to track miscellaneous mi stuff

   Jupyter Notebook 3