63 citations · 144 across the 7 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 12 cited
A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations
Bilal Chughtai, Lawrence Chan, Neel Nanda
Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study…
cs.LG2023★ 54 cited
Progress measures for grokking via mechanistic interpretability
Neel Nanda, Lawrence Chan, Tom Lieberum +2
Neural networks often exhibit emergent behavior, where qualitatively new capabilities arise from scaling up the amount of parameters, training data, or training steps. One approach…