63 citations · 81 across the 3 of their papers we have counts for
3 papers
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Kenneth Li, Aspen K. Hopkins, David Bau +3
Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics,…
An Interpretability Illusion for BERT
Tolga Bolukbasi, Adam Pearce, Ann Yuan +4
We describe an "interpretability illusion" that arises when analyzing the BERT model. Activations of individual neurons in the network may spuriously appear to encode a single, sim…
XRAI: Better Attributions Through Regions
Andrei Kapishnikov, Tolga Bolukbasi, Fernanda Viégas +1
Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this…