claim
active
claim:belief-may-be-linearly-represented-only-within-a-subspace-of-representation-spaceBelief may be linearly represented only within a subspace of representation space
Speculative interpretation of breakdown.
Source paper
extracted_from(2025) · Eric Bigelow · Daniel Wurgaft · YingQiao Wang · Noah D. Goodman +3
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Limit of LRH regime.
Questions (2)
question
- Open question.
- Open question.
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.
- Interpretive synthesis of DIM and cone intervention successes
- Theoretical aim.
- Open question A.1.1a.2.
- The idea that features are encoded as directions in activation space.
- Theoretical open question about the geometry of truth in LLMs raised in Discussion
- Activations are sums of sparse features living in subspaces.
- Load-bearing interpretive claim about the layer-specificity of Burger et al.'s finding.
- The hypothesis that models internalize concepts as approximately linear directions in representation space; used to interpret MDS injection behavior