Pinned Loading

1. mixing-mechs mixing-mechs Public

   Official code for "Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context"

   Jupyter Notebook 10 6

2. PISCES PISCES Public

   🪝PISCES - Precise In-Parameter Suppression for Concept EraSure in Large Language Models

   Python 12 1

3. Feature-Descriptions Feature-Descriptions Public

   Enhancing Automated Interpretability with Output-Centric Feature Descriptions

   Jupyter Notebook 11 1

4. mechinterp mechinterp Public

   Library for easily using interpretability techniques in transformer models

   Python 6