Pinned Loading

1. tiny-sleepers tiny-sleepers Public

   A replication of Anthropic's Sleeper Agents and Stage-wise Model Diffing on a TinyStories language model.

   Jupyter Notebook 20

2. BIXRL BIXRL Public

   The code for "Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning"

   Python

3. clarifying-EM/model-organisms-for-EM clarifying-EM/model-organisms-for-EM Public

   Code repo for the model organisms and convergent directions of EM papers.

   Python 86 49