54 citations · 77 across the 8 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 6 cited
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla
Tom Lieberum, Matthew Rahtz, János Kramár +4
\emph{Circuit analysis} is a promising technique for understanding the internal mechanisms of language models. However, existing analyses are done in small models far from the stat…
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…