question
active
question:is-incomplete-sae-reconstruction-due-to-a-fundamental-architecture-limitation-e-g-truly-nonlinear-features-or-a-mundane-causeIs incomplete SAE reconstruction due to a fundamental architecture limitation (e.g. truly nonlinear features) or a mundane cause?
Open question in limitations.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Limitation statement.
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.
- SAE reconstruction error direction and norm are largely linearly predictable from the activation vectorfinding0.786Errors are structured not random.
- Features act as local patch detectors.
- Core critique of sparse autoencoders: they break the geometric structure of representations, making it harder to see the big picture.
- Related to point-based simplicial limit.
- Source of mismatch.
- Geometric explanation for prior negative results.
- Quantifies SAE reconstruction damage.
- Multiplicity of SAE curve features is an artifact of the featurizer, not a property of the network.claim0.761Reinterpretation of curve detectors.