Safety, Ethics & Governance · advanced · concept 174 of 176

⚖️Mechanistic Interpretability

Reverse engineering a network's internal computation into human-readable parts: features, the circuits that combine them, and how information moves between layers. Sparse autoencoders are the main tool for pulling interpretable features out of layers whose individual neurons each represent many unrelated things. It differs from feature-attribution methods, which say which inputs mattered without describing the mechanism that used them.