Popular repositories Loading

1. 1L-Sparse-Autoencoder 1L-Sparse-Autoencoder Public

   Python 139 15

2. Crosscoders Crosscoders Public

   Python 59 1

3. Grokking Grokking Public

   A Mechanistic Interpretability Analysis of Grokking

   Python 28 3

4. neel-plotly neel-plotly Public

   A very hacky set of functions for getting plotly to do what I want when doing mech interp research, designed to be compatible with PyTorch

   Python 14 4

5. Neuroscope Neuroscope Public

   Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons

   Python 14 5

6. Stable-Diffusion-Interp Stable-Diffusion-Interp Public

   Python 9