SOURCE-LINKED INTELLIGENCE

Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Mechanistic interpretability defines features as the fundamental units of a neural network and circuits as the weighted subgraphs that carry out its computation. Because individual neurons are polysemantic, Cross-Layer Transcoders (CLTs) were introduced as a way to approximate a model's circuits by generating an attribution graph. The nodes of that graph, however, are unlabeled features: reading a graph means pruning it and then working out by hand what each surviving node means. To make CLTs easier to use for circuit discovery, we introduce Circuit-Diff, which intervenes on the model itself w

Read original source ↗ Open in workspace

recordType

paper

region

Global