Popular repositories Loading

1. ARENA_evals ARENA_evals Public

   HTML 2 4

2. paper-replications paper-replications Public

   Replication of main results in Elhage (2022) - Toy Models of Superposition

   Jupyter Notebook

3. representation-engineering-forked representation-engineering-forked Public

   Forked from andyzoujm/representation-engineering

   Representation Engineering: A Top-Down Approach to AI Transparency

   Python

4. jailbreaking_interp jailbreaking_interp Public

   Python

5. chloeli-15.github.io chloeli-15.github.io Public

   HTML

6. ARENA_img ARENA_img Public

   Diagrams and images used in the ARENA materials

   HTML 1