Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
Researchers have introduced "Contribution Weights," a novel metric for analyzing self-attention transformers in large language models. This new metric goes beyond traditional attention weights by incorporating the geometric properties of value vectors, offering a more accurate measure of a token's influence. The study demonstrates that Contribution Weights effectively identify semantically critical tokens and provides new insights into the functional role of "attention sinks," revealing their active role in stabilizing representations rather than merely storing information. AI
IMPACT Provides a more accurate method for interpreting LLM behavior, potentially improving model analysis and debugging.