Sparse Autoencoders Find Highly Interpretable Features in Language Models
Cunningham, Ewart, Riggs, Huben, Sharkey (2023)
foundational, interpretability
Papers
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Bricken, Templeton, Batson et al. (Anthropic) (2023)
foundational, dictionary-learning, anthropic
Softmax Linear Units (SoLU)
Elhage, Hume, Olsson et al. (Anthropic) (2022)
foundations, architecture, anthropic
Toy Models of Superposition
Elhage, Hume, Olsson et al. (Anthropic) (2022)
foundations, superposition, anthropic
k-Sparse Autoencoders
Makhzani & Frey (2013)
foundations, architecture