finding
active
finding:absolute-value-model-n-100-m-40-computes-abs-in-superposition-when-features-are-sparseAbsolute value model (n=100, m=40) computes abs in superposition when features are sparse
Computation in superposition.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionmentions
Claims (2)
claim
- Supported by abs model.
- Neuroscience implication.
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.
- Mechanistic motif.
- Without superposition.
- Model computing abs(x) in superposition.
- Baseline.
- Core demonstration.
- superposition is deeply linked to the ability to identify and enumerate over all features in a modelquote0.760Safety rationale.
- Mirrors real networks.
- Claim about current practical feasibility and efficiency of 2-way associative implementations.