finding
active
finding:in-vit-last-layer-top-10-k-fac-eigenvectors-have-over-2x-activation-on-clean-vs-memorized-data-svd-shows-no-pattern

In ViT last layer, top 10% K-FAC eigenvectors have over 2x activation on clean vs memorized data; SVD shows no pattern

Vision disentanglement.

Source paper

extracted_from
From Memorization to Reasoning in the Spectrum of Loss Curvature
(2025) · Merullo, Jack · Vatsavaya, Srihita · Bushnaq, Lucius · Lewis, Owen

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.