claim
active
claim:45b37a34b39527e7Activation manifolds and behavior manifolds are approximately isometric across cyclic and sequential concepts.
Neighborhood — ranked by edge-count
Communities (3)
community
- Explores geometry of activation/behavior manifolds to enable selective, non-destructive concept interventions.
- Concepts encoded as curved manifolds and circular structures in LLM activation spaces.
- Neural network activation and behavior manifolds maintain geometric correspondence, enabling intervention optimization across language models and vision tasks.
Vectors (1)
vector
- Convergent Representationsaddresses_vector
Source docs (1)
source_doc
- 2026-05-14_phil-trans-A-goodfire-aboutblank-impact.mdextracted_from
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.
- The paper's causal explanation for why representation and behavior geometry both appear circular for days of the week.
- Central empirical result showing causal coupling between representation and behavior geometry across multiple substrates and modalities.
- The low-dimensional geometric structure discovered in neural activation space; contrasted with linear/Euclidean geometry.
- One-dimensional curved surface in output probability space; the paper shows this mirrors representation manifold structure.
- Generalization finding from the full paper extending beyond days-of-week to other structured concepts.
- The paper's finding that the alignment holds in both directions — from representation to behavior and from behavior back to representation space.