claim
active
claim:multiplicity-of-sae-curve-features-is-an-artifact-of-the-featurizer-not-a-property-of-the-networkMultiplicity of SAE curve features is an artifact of the featurizer, not a property of the network.
Reinterpretation of curve detectors.
Source paper
extracted_from(2026) · Thomas Fel · Matthew Kowal · Mozes Jacobs · Dron Hazra +21
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Curve manifold recovery.
Claims (1)
claim
- Retrodiction of known phenomenon.
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.
- Claim that feature grounding enables interpretability metrics.
- Core critique of sparse autoencoders: they break the geometric structure of representations, making it harder to see the big picture.
- Appendix I.
- Extension of mechanistic interpretability findings to the metacognitive domain
- Core concern.
- Novel finding that agentic self-evaluation of emotionality correlates with feature persistence
- Observed across SAE scales, e.g., 'San Francisco' split into 11 features.
- Top SAE features on the years manifold show localized smooth tuning curves with overlapping supportfinding0.765Reminiscent of population coding.