43 citations · 73 across the 11 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 3 cited
Challenges with unsupervised LLM knowledge discovery
Sebastian Farquhar, Vikrant Varma, Zachary Kenton +3
We show that existing unsupervised methods on large language model (LLM) activations do not discover knowledge -- instead they seem to discover whatever feature of the activations…
cs.LG2023★ 2 cited
Explaining grokking through circuit efficiency
Vikrant Varma, Rohin Shah, Zachary Kenton +2
One of the most surprising puzzles in neural network generalisation is grokking: a network with perfect training accuracy but poor generalisation will, upon further training, trans…