🧑🔬 Tom Lieberum — papers of 20232 papers · all years of Tom LieberumProgress measures for grokking via mechanistic interpretabilityNeel Nanda, Lawrence Chan, Tom Lieberum, et al.arXiv:2301.05217 · 207 citationsDoes Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in ChinchillaTom Lieberum, Matthew Rahtz, Janos Kramar, et al.arXiv:2307.09458 · 51 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/tom-lieberum/year/2023/