finding
active
finding:absolute-value-model-uses-two-instances-of-asymmetric-superposition-plus-inhibitionAbsolute value model uses two instances of asymmetric superposition plus inhibition
Mechanistic motif.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionmentions
Claims (1)
claim
- Supported by abs model.
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.
- Absolute value model (n=100, m=40) computes abs in superposition when features are sparsefinding0.845Computation in superposition.
- Without superposition.
- Model computing abs(x) in superposition.
- Mathematical derivation from Saxe-style loss.
- E1 qualitative finding demonstrating anchor rebinding of strong arithmetic prior
- The model appears to encode truth differently under passive versus active truth evaluation prompts.claim0.741Key finding from Section 5 based on low cosine similarity between no-prompt and ask-correct probes.
- Cost of removing superposition.
- Basis of phenomenological argument.