Pinned Loading

1. TransformerLensOrg/CircuitsVis TransformerLensOrg/CircuitsVis Public

   Mechanistic Interpretability Visualizations using React

   Jupyter Notebook 217 32

2. rl-ltl rl-ltl Public

   Codebase for my honours thesis: https://danbraunai.github.io/files/thesis.pdf

   Python 2

3. interpreting-rl-behavior/interpreting-rl-behavior.github.io interpreting-rl-behavior/interpreting-rl-behavior.github.io Public

   Code for the site https://interpreting-rl-behavior.github.io/

   JavaScript

4. interpreting-rl-behavior/models--interpreting-rl-behavior interpreting-rl-behavior/models--interpreting-rl-behavior Public

   Models and experiments used in https://interpreting-rl-behavior.github.io/

   Python 2

5. ApolloResearch/sample ApolloResearch/sample Public template

   Repository with sample code using Apollo's suggested engineering practices

   Python 7

6. simple_stories_train simple_stories_train Public

   Trains small LMs. Designed for training on SimpleStories

   Python 6 1