question
active
question:what-should-be-unit-of-analysis-for-decomposing-a-representationWhat should be unit of analysis for decomposing a representation?
Structured sparsity interpretability question.
Source paper
extracted_from(2026) · Thomas Fel · Matthew Kowal · Mozes Jacobs · Dron Hazra +21
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Motivation for lifting atoms to blocks.
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 central question of whether representational geometry implies corresponding computational structure
- Central open question A.1.1a.1.
- Defining property of Schrödinger compositional theory
- Core slogan encapsulating the paradigm shift of VPD.
- Investigation of whether a distributed representation can be further decomposed into sub-representations encoding component identities.
- How a neural network encodes a semantic concept internally, argued to be better captured by manifolds than by atomic features.