91 citations · 189 across the 19 of their papers we have counts for
4 papers · 1 filter
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…
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…
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas +27
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 20…
SIRL: Similarity-based Implicit Representation Learning
Andreea Bobu, Yi Liu, Rohin Shah +2
When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the ta…