AI Dynamics

Global AI News Aggregator

About

Research Analysis: Massive Activations and Attention Sinks in Transformers

Another by Yann LeCun! “The Spike, the Sparse and the Sink” This paper shows that massive activations and attention sinks come from the same pre-norm Transformer pipeline rather than being separate anomalies. Early SwiGLU blocks act like directional quadratic amplifiers,

→ View original post on X — @askalphaxiv