Circuit Tracing: Revealing Computational Graphs in Language Models

We describe an approach to tracing the “step-by-step” computation involved when a model responds to a single prompt.

Circuit Tracing: Revealing Computational Graphs in Language Models × Transformer Circuits Thread Circuit Tracing: Revealing Computational Graphs in Language Models Circuit Tracing: Revealing Computational Graphs in Language Models We introduce a method to uncover mechanisms underlying behaviors of language models. We produce graph descriptions of the model’s computation on prompts of interest by tracing individual computational steps in a “replacement model”. This replacement model substitutes a more interpretable component (here, a “cross-layer transcoder”) for parts of the underlying model (

saved by

• Karan MJ
• Tasha Pais
• Jenny Sun
• Samuel Lo
• Jennifer Zhao
• Matthew Wang
• Asher P
• Vyom Pathak
• Thu Than
• Lydia Nottingham
• Logan Graves
• Eric Huang

related reading

• On the Biology of a Large Language Modeltransformer-circuits.pub
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Transformer Circuits Threadtransformer-circuits.pub
• Language Model Circuits Are Sparse in the Neuron Basis | Transluce AItransluce.org
• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• Towards Automated Circuit Discovery for Mechanistic Interpretabilityarxiv.org
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• Circuit Tracing in Vision–Language Models:Understanding the Internal Mechanisms of Multimodal Thinkingarxiv.org
• Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
• In-context Learning and Induction Headstransformer-circuits.pub
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub