arXiv - CSCL: "How does GPT-2 compute greater-than?: Interpretin…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. (arXiv:2305.00586v5 [cs.CL] UPDATED)

http://arxiv.org/abs/2305.00586 #arXiv #NLProc

Nov 03, 2023, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation