CLT-Forge
A Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph Visualization
- 111
- Python
- MIT
- 4 mo ago
A Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph Visualization
HandBrake wrapper that makes it seamlessly available as a local dependency
Interactive lab for attribution graphs & circuit tracing — replace polysemantic neurons with monosemantic features, trace causal paths, and patch a real two-hop reasoning circuit. MIT Tech Review 2026 Breakthrough tech.