method
active
method:circuit-tracing

Circuit tracing

Anthropic technique revealing computational pathways in Claude.

Neighborhood — ranked by edge-count

Institutes (1)

institute
  • Anthropic
    studies
    Lab behind Claude models and Constitutional AI training approach; represents highest baseline scores and lowest prompt lift.

Related by similarity (8)

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.

  • Circuit Findingmethod0.837
    Interpretability technique for identifying functional sub-circuits in neural networks, supported by pyvene
  • Causal Tracingconcept0.818
    Mechanistic interpretability technique for locating factual associations, mentioned as future work direction.
  • Circuit Analysisconcept0.807
    Fine-grained approach to identifying specific network components responsible for reflection, mentioned as future direction.
  • Circuits Threadframework0.789
    An open scientific collaboration hosted on Distill slack studying the inner workings of neural networks via zoomed-in mechanistic investigation
  • Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed
  • Interactive tool for visualizing and inspecting learned binary logic circuits using modified DigitalJS library
  • Circuit Motifconcept0.772
    A recurring, abstract pattern found in circuits (e.g., equivariance, unioning over cases), inspired by circuit motifs in systems biology
  • Default circuitsconcept0.769
    Circuits active by default, e.g. can't-answer, suppressed by contrary evidence.