thinker:mozes-jacobsMozes Jacobs
Authored papers (1)
Lifting the featurizer's atom from a direction to a block of directions recovers concept manifolds that SAEs shatter, and block sparsity is the MAP-matched prior for a representation that is a sparse Minkowski sum of low-dimensional manifolds. The paper introduces block-sparse featurizers (BSFs) in three variants: Vanilla (top-k blocks by norm, untied encoder), Grassmannian (tied encoder with orthonormal charts), and Group Lasso (block soft-threshold). On a synthetic manifold-superposition toy, all three reach per-block R² of 0.93–0.97 against an oracle of 0.99, while a TopK SAE collapses to 0.53. On DINOv3 ViT-B, a minimum-description-length analysis at the 20% distortion floor shows blocks of dimension 2–4 describe activations in fewer bits than b=1 SAEs at every dictionary width and sparsity, and stable rank saturates near 3 even when b=16 is allowed. In InceptionV1, the curve-detector neurons and SAE atoms are fragments of one curve manifold, whose first three Fourier harmonics carry 89% of variance (59/18/12%) and survive a matched null by factors of 470 and 314. A DINOv3 block tracks sun luminance and shadow across twelve Blender models, and SDXL blocks support manifold steering, as in the pretzel block. The implication is that a featurizer is a hypothesis about the data-generating process, so interpretability should infer what the atoms must be rather than assume them. Blocks are one answer, matched to vision but probably not to language.
More papers — OpenAlex / S2
Affiliations (1)
- Harvard University(institute)
Co-authors (12)
- Atticus Geiger9 shared
- Dron Hazra9 shared
- Ekdeep Singh Lubana9 shared
- Jack Merullo9 shared
- Lee Sharkey9 shared
- Matthew Kowal9 shared
- Thomas Fel9 shared
- Thomas Serre9 shared
- Usha Bhalla9 shared
- Aiden Swann6 shared
- Can Rager6 shared
- Curt Tigges6 shared
Other inbound relations (1)
Recent mentions (1)
- papers-typedfel-2026-structuring-sparsity.md