Circuit (mechanistic interpretability)

An inference path across features that constitutes a computational subgraph in a trained model

Neighborhood — ranked by edge-count

paper

concept

Circuit Interpretability
related_to
Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Features (mechanistic interpretability)concept0.808
Functionally significant directions in the residual stream that organize activations in mechanistic interpretability
Circuits could act as an epistemic foundation for interpretability by breaking down model behavior into falsifiable statements about small subgraphs.claim0.786
Normative vision for how the circuits agenda could resolve the pre-paradigmatic state of interpretability
Circuit Motifconcept0.761
A recurring, abstract pattern found in circuits (e.g., equivariance, unioning over cases), inspired by circuit motifs in systems biology
Circuit Analysisconcept0.761
Fine-grained approach to identifying specific network components responsible for reflection, mentioned as future direction.
interpretabilityconcept0.742
The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
Interactive Circuit Visualizationmethod0.740
Interactive tool for visualizing and inspecting learned binary logic circuits using modified DigitalJS library
Recurrent Logic Circuitconcept0.732
The key novel property of DiffLogic CA — logic gate networks that are recurrent both spatially and temporally
Circuits Frameworkframework0.732
Mechanistic interpretability framework for understanding neural network computation as circuits of features