finding
active
finding:feature-475549-activates-on-inputs-ending-in-1-and-promotes-tokens-ending-in-2-max-activating-on-tokens-preceding-2-in-lists-and-timestampsFeature 475549 activates on inputs ending in 1 and promotes tokens ending in 2; max-activating on tokens preceding 2 in lists and timestamps
Structured number feature.
Source paper
extracted_fromNeighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Closing claim.
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.
- More general greater-than feature.
- Structured number feature.
- Abstract parity feature.
- Unexpected behavior; may be general small-number detector.
- Feature represents the 'addition' function abstractly.
- Logit attribution heatmaps and max-activating examples disagree for Features 425104 and 349410finding0.774Limitation.
- Design choice validated empirically.
- More complex than simple comparison.