finding
active
finding:adversarial-vulnerability-increases-3x-as-superposition-forms-and-tracks-features-per-dimension

Adversarial vulnerability increases >3x as superposition forms and tracks features per dimension

L2 attacks max norm 0.1 of average input norm.

Source paper

extracted_from
Toy Models of Superposition
(2022) ·

Neighborhood — ranked by edge-count

Papers (1)

paper

Claims (1)

claim