Kevin Ro Wang

Publication Activity (10 Years)

Years Active: 2022-2023
Publications (10 Years): 3

Top Topics

Multilayer Perceptron

Biologically Plausible

Neural Architecture

Top Venues

Publications

Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, Jacob Steinhardt
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small. ICLR (2023)
Mor Geva, Avi Caciularu, Kevin Ro Wang, Yoav Goldberg
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space. EMNLP (2022)
Mor Geva, Avi Caciularu, Kevin Ro Wang, Yoav Goldberg
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space. CoRR (2022)