question
active
question:what-is-the-provenance-of-model-exclusive-features-explicit-training-vs-data-artifactsWhat is the provenance of model-exclusive features (explicit training vs data artifacts)?
Future work.
Source paper
extracted_from(2026) · Thomas Jiralerspong · Trenton Bricken
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Limitation.
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.
- Authors argue features are model properties because logit effects and ablations are consistent with feature interpretations
- Mixed picture for diffing.
- Appendix C.5/C.7.
- Primary unexpected empirical observation.
- Authors take agnostic position on ontological status but universality evidence pushes toward features being real
- Motivation for using sparsity-based dictionary learning on language models
- Features writing predominantly to one model.
- Are there model structures that account for memorization and generalization across large swaths of training data?question0.762Aggregate analysis motivation.