claim
active
claim:results-collectively-provide-strong-evidence-that-some-version-of-the-superposition-hypothesis-and-linear-representation-hypothesis-is-trueResults collectively provide strong evidence that some version of the superposition hypothesis and linear representation hypothesis is true
Authors' overall conclusion from number of interpretable features, activation-level correspondence to intensity, sensible logit weights, and interference weights
Source paper
extracted_from(2024) · Marc Carauleanu · Michael Vaiana · Judd Rosenblatt · Cameron Berg +1
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Superposition HypothesissupportsCore theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition
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.
- Position on LRH.
- Open question A.1.1a.2.
- Steering derived from LRH.
- The hypothesis that models internalize concepts as approximately linear directions in representation space; used to interpret MDS injection behavior
- Authors' hedged interpretation.
- Explains robust models being more robust than expected.
- Posed on SAE results.
- Central thesis.