State of Transformer Interpretability

3 papers · avg viability 4.7

View topic page

Top papers

Interpretable-by-Design Transformers via Architectural Stream Independence(7.0)
Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks(4.0)
What Helps -- and What Hurts: Bidirectional Explanations for Vision Transformers(3.0)