Edge-based circuits in vision transformers can be automatically recovered to explain and steer model computations for classification and adversarial behaviors.
In: Proceedings of the International Conference on Learning Representations (2021) 7, 9, 18
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers
Edge-based circuits in vision transformers can be automatically recovered to explain and steer model computations for classification and adversarial behaviors.