2 papers
cs.LG2025
On the geometry and topology of representations: the manifolds of modular addition
Gabriela Moisescu-Pareja, Gavin McCracken, Harley Wiltzer +4
The Clock and Pizza interpretations, associated with architectures differing in either uniform or learnable attention, were introduced to argue that different architectural designs…
cs.LG2025
Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
Gavin McCracken, Gabriela Moisescu-Pareja, Vincent Letourneau +2
We propose a testable universality hypothesis, asserting that seemingly disparate neural network solutions observed in the simple task of modular addition are unified under a commo…