concept
active
concept:default-circuitsDefault circuits
Circuits active by default, e.g. can't-answer, suppressed by contrary evidence.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Hallucination circuit.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Interpretability technique for identifying functional sub-circuits in neural networks, supported by pyvene
- Mechanistic interpretability framework for understanding neural network computation as circuits of features
- A goal in mechanistic interpretability to identify sparse computational subgraphs; VPD promotes sparse parameter circuits.
- A recurring, abstract pattern found in circuits (e.g., equivariance, unioning over cases), inspired by circuit motifs in systems biology
- An open scientific collaboration hosted on Distill slack studying the inner workings of neural networks via zoomed-in mechanistic investigation
- Motivating example.
- Anthropic technique revealing computational pathways in Claude.
- Hypothesis that discretization finds minimum-size circuits equivalent to minimal algorithmic descriptions of patterns