method
active
method:feature-interpretability-rubricFeature Interpretability Rubric
14-point scoring rubric for human evaluation of feature interpretability covering confidence, activation consistency, logit consistency, and specificity
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.
- The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
- Socio-philosophical open question.
- Functionally significant directions in the residual stream that organize activations in mechanistic interpretability
- Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed
- New affordance of features beyond monitoring/steering.
- Method using large language models (Claude) to generate and test explanations of features at scale
- Benchmark discipline.