question
active
question:whether-real-representations-satisfy-the-manifold-assumption-and-whether-manifold-survives-as-the-right-name-remains-an-open-problemWhether real representations satisfy the manifold assumption, and whether "manifold" survives as the right name, remains an open problem
Acknowledged open issue in footnote.
Source paper
extracted_from(2026) · Usha Bhalla · Thomas Fel · Can Rager · Sheridan Feucht +8
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Data-generating process: activation is sparse sum of low-dimensional manifold points.
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.
- Features may not be strictly one-dimensional objects; higher-dimensional feature manifolds may exist in model representationshypothesis0.783Extension of superposition hypothesis to account for continuous families of features
- Manifold structure is present in representations and causally influences downstream behaviorclaim0.760Interpretation of steering results.
- One-dimensional curved surface in internal activation space; the paper demonstrates alignment with behavior manifold.
- The procedure of fitting a one-dimensional manifold (path) to clusters in activation or behavior space to capture the geometric structure of a concept.
- The paper's finding that the alignment holds in both directions — from representation to behavior and from behavior back to representation space.
- Neuroscience-motivated prediction.
- Implication for interpretability.
- Generalization finding from the full paper extending beyond days-of-week to other structured concepts.