6 citations · 15 across the 5 of their papers we have counts for
5 papers
Improving Dictionary Learning with Gated Sparse Autoencoders
Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith +5
Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by find…
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…
The Hydra Effect: Emergent Self-repair in Language Model Computations
Thomas McGrath, Matthew Rahtz, Janos Kramar +2
We investigate the internal structure of language model computations using causal analysis and demonstrate two motifs: (1) a form of adaptive computation where ablations of one att…
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…
Power-seeking can be probable and predictive for trained agents
Victoria Krakovna, Janos Kramar
Power-seeking behavior is a key source of risk from advanced AI, but our theoretical understanding of this phenomenon is relatively limited. Building on existing theoretical result…