Kevin Ro Wang

According to our database, Kevin Ro Wang authored at least 2 papers between 2022 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small.

Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, Jacob Steinhardt

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

Mor Geva, Avi Caciularu, Kevin Ro Wang, Yoav Goldberg

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022