Circuit Tracing: Revealing Computational Graphs in Language Models
transformer-circuits.pub ↗(Anthropic, 2025) - introduces cross-layer transcoders and attribution graphs to construct an interpretable replacement model; enables prompt-level circuit tracing of feature-to-feature causal interactions.
(Anthropic, 2025) - introduces cross-layer transcoders and attribution graphs to construct an interpretable replacement model; enables prompt-level circuit tracing of feature-to-feature causal interactions.
This entry links to an external website rather than a GitHub repository, so there's no README to display here.