finding
active
finding:robust-and-non-robust-toy-models-trained-at-the-same-sparsity-have-strikingly-similar-superposition-geometries-with-robust-ones-having-less-superposition

Robust and non-robust toy models trained at the same sparsity have strikingly similar superposition geometries, with robust ones having less superposition.

Figure 4.

Source paper

extracted_from
Adversarial Examples Are Not Bugs, They Are Superposition
(2025) · Gorton, Liv · Lewis, Owen

Neighborhood — ranked by edge-count