Popular repositories Loading

1. world-models world-models Public

   Extracting spatial and temporal world models from LLMs

   Jupyter Notebook 258 25

2. sparse-probing-paper sparse-probing-paper Public

   Sparse probing paper full code.

   Jupyter Notebook 67 11

3. universal-neurons universal-neurons Public

   Universal Neurons in GPT2 Language Models

   Jupyter Notebook 30 7

4. sindy_mio_paper sindy_mio_paper Public

   Code for Learning Sparse Nonlinear Dynamics via Mixed Integer Optimization

   Python 16 5

5. llm-context-neurons llm-context-neurons Public

   Find context neurons in Pythia models.

   Python 13 3

6. mats_sae_training mats_sae_training Public

   Forked from decoderesearch/SAELens

   Training Sparse Autoencoders on Language Models

   HTML 3 1