Skip to content
conftrace_

transformer explanation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

token attribution (1) syntactic head (1) gradient-based attribution (1) transformer model (1) class activation token (1) layer-wise relevance propagation (1) gradient attribution (1) attention weight (1) skip connection (1) attention head (1)

Papers

Better Explain Transformers by Illuminating Important Information EACL 2024 AttCAT: Explaining Transformers via Attentive Class Activation Tokens NeurIPS 2022