Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space Mor Geva author Avi Caciularu author Kevin Wang author Yoav Goldberg author 2022-12 text Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Yoav Goldberg editor Zornitsa Kozareva editor Yue Zhang editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates conference publication geva-etal-2022-transformer 10.18653/v1/2022.emnlp-main.3 https://aclanthology.org/2022.emnlp-main.3/ 2022-12 30 45