finding
active
finding:fuzzy-induction-heads-match-words-across-languages-antonyms-structural-positions-and-kinship-termsFuzzy induction heads match words across languages, antonyms, structural positions and kinship terms
Variety of fuzzy matching found.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central interpretation of induction case study.
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.
- Induction performed in the feature basis rather than token space.
- Mechanistic circuits in transformers documented by Olsson et al. 2022, cited as evidence for pattern-repository assumption
- A follow-up paper extending the framework and induction head concept to larger more realistic models
- Central empirical claim of the paper; induction heads are shown to be the mechanism for powerful in-context learning
- Fuzziness lives in QK.
- The mechanistic explanation of how induction heads are implemented in two-layer models
- Early-layer induction heads do literal copying while mid-layer heads do fuzzier inductionfinding0.751Layer-dependent induction on Haiku 3.5.
- Fuzzy poetry induction head OV circuit is identical to literal induction (newline value to 'say \n' output)finding0.748Copying behavior unchanged.