EasyDeepLearn

How much can you interpret a model from attention weights?

hard

Answer

  • Attention weights are a noisy signal for interpretability.
  • High weight ≠ 'the model uses this token'.
  • Multiple heads look at overlapping things; residual streams carry lots of info regardless of attention.
  • Better tools: attribution methods (integrated gradients, attention rollout), probing linear classifiers on hidden states, mechanistic interpretability (Anthropic's circuits).
  • Attention maps are a starting point, not a proof.
Check yourself — multiple choice
  • Attention weights are perfect explanations
  • Attention is a noisy interpretability signal — use gradients, probes, mechanistic tools too
  • Attention weights are random
  • Attention interpretability is a solved problem

Attention weights ≠ explanation — noisy signal; complement with gradients/probes/circuits.

#transformers#attention#interpretability

Practise Deep Learning

214 interview questions in this topic.

Related questions