Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small | Deep Learning JP

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

2026年06月16日 OKUMURA Rika DL Papers 2026, dls-2026, papers

【DL輪読会】Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small by @DeepLearning2023

%d人のブロガーが「いいね」をつけました。