claim
active
claim:interpretability-s-usefulness-must-be-assessed-against-non-interpretability-baselinesInterpretability's usefulness must be assessed against non-interpretability baselines
Benchmark discipline.
Source paper
extracted_from(2025) · Lee Sharkey · Bilal I. Chughtai · Joshua Batson · Jack W. Lindsey +25
Neighborhood — ranked by edge-count
Papers (1)
paper
- Open Problems in Mechanistic Interpretabilitycitesmentions
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.
- Motivation for the release.
- Limitation.
- Caveat on metric.
- Socio-philosophical open question.
- The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
- Forward-looking suggestion for how inner interpretability could extend the indicator method
- Prioritization argument.
- Caveat after the evaluator pitfall.