“Attention Approximates Sparse Distributed Memory”, Trenton Bricken, Cengiz Pehlevan2021-11-10 (self-attention, GPT-2 nonfiction, neuroscience)⁠:

While Attention has come to be an important mechanism in deep learning, there remains limited intuition for why it works so well. Here, we show that Transformer Attention can be closely related under certain data conditions to Kanerva’s Sparse Distributed Memory (SDM), a biologically plausible associative memory model.

We confirm that these conditions are satisfied in pre-trained GPT-2 Transformer models.

We discuss the implications of the Attention-SDM map and provide new computational and biological interpretations of Attention.