Mechanistic Interpretability: Circuits, Induction Heads - Interactive | Michael Brenndoerfer

Reverse-engineer transformer networks into human-understandable algorithms by identifying circuits, induction heads, and mechanistic discoveries.

Mechanistic InterpretabilityLink Copied When a language model predicts that "The Eiffel Tower is located in" should be followed by "Paris," what computation produced that answer? Which weights fired, which attention heads activated, and which neurons collectively encoded the relevant geographic knowledge? Mechanistic interpretability is the research program that asks precisely these questions. Rather than treating a neural network as a black box that produces outputs from inputs, mechanistic interpretability tries to reverse-engineer the model into a human-understandable algorithm. It seeks…

saved by

• Clementine Yang

related reading

• A Comprehensive Mechanistic Interpretability Explainer & Glossary — Neel Nandaneelnanda.io
• In-context Learning and Induction Headstransformer-circuits.pub
• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• On the Biology of a Large Language Modeltransformer-circuits.pub
• Transformer Circuits Threadtransformer-circuits.pub
• Towards Automated Circuit Discovery for Mechanistic Interpretabilityarxiv.org
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• Interpreting Language Model Parametersgoodfire.ai
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• Induction heads - illustrated — LessWronglesswrong.com
• Introduction to Mechanistic Interpretability - by Sarahblog.bluedot.org