165 citations · 287 across the 6 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.AI2021★ 103 cited
Acquisition of Chess Knowledge in AlphaZero
Thomas McGrath, Andrei Kapishnikov, Nenad Tomašev +5
What is learned by sophisticated neural network agents such as AlphaZero? This question is of both scientific and practical interest. If the representations of strong neural networ…
cs.CL2021★ 11 cited
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…