2 code implementations • 15 Sep 2023 • Hoagy Cunningham, Aidan Ewart, Logan Riggs, Robert Huben, Lee Sharkey
One hypothesised cause of polysemanticity is \textit{superposition}, where neural networks represent more features than they have neurons by assigning features to an overcomplete set of directions in activation space, rather than to individual neurons.
no code implementations • 15 Sep 2023 • Robert Huben, Valerie Morris
The transformer architecture is widely used in machine learning models and consists of two alternating sublayers: attention heads and MLPs.