LESSWRONGTags
LW

Machine Learning (ML)

•

Applied to Influence functions - why, what and how by Nina Rimsky 12d ago

•

Applied to Mech Interp Challenge: September - Deciphering the Addition Model by TheMcDouglas 14d ago

•

Applied to Expanding the Scope of Superposition by Derek Larson 15d ago

•

Applied to Explaining grokking through circuit efficiency by Vikrant Varma 20d ago

•

Applied to Report on Analyzing Connotation Frames in Evolving Wikipedia Biographies by Maira 1mo ago

•

Applied to Apply to a small iteration of MLAB to be run in Oxford by RP 1mo ago

•

Applied to Is this the beginning of the end for LLMS [as the royal road to AGI, whatever that is]? by Bill Benzon 1mo ago

•

Applied to Causality and a Cost Semantics for Neural Networks by scottviteri 1mo ago

•

Applied to Against Almost Every Theory of Impact of Interpretability by Charbel-Raphaël 1mo ago

•

Applied to Google DeepMind's RT-2 by SandXbox 2mo ago

•

Applied to The positional embedding matrix and previous-token heads: how do they actually work? by AdamYedidia 2mo ago

•

Applied to Mech Interp Challenge: August - Deciphering the First Unique Character Model by TheMcDouglas 2mo ago

•

Applied to Trading off compute in training and inference (Overview) by Pablo Villalobos 2mo ago

•

Applied to Visible loss landscape basins don't correspond to distinct algorithms by Mikhail Samin 2mo ago

•

Applied to Thoughts on Loss Landscapes and why Deep Learning works by beren 2mo ago

•

Applied to Introductory Textbook to Vision Models Interpretability by jeanne_ 2mo ago