method
active
method:circuit-findingCircuit Finding
Interpretability technique for identifying functional sub-circuits in neural networks, supported by pyvene
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.
- Fine-grained approach to identifying specific network components responsible for reflection, mentioned as future direction.
- Anthropic technique revealing computational pathways in Claude.
- An open scientific collaboration hosted on Distill slack studying the inner workings of neural networks via zoomed-in mechanistic investigation
- Circuits active by default, e.g. can't-answer, suppressed by contrary evidence.
- 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.
- Lists issues: concept-based tasks, flawed decomposition, low faithfulness.
- Automates identifying task-relevant subgraphs.