Variengien, Alexandre
2 papers on CoChat
Most cited papers
- Verified
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
Hanna, M., Liu, O., & Variengien, A. (2023) · arXiv
Explainable Artificial Intelligence (XAI)Topic Modeling
Cited by 84
- Verified
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
Wang, K., Variengien, A., Conmy, A., Shlegeris, B., & Steinhardt, J. (2022) · arXiv
Explainable Artificial Intelligence (XAI)Topic Modeling
Cited by 52
Go further with a free account
Verify every reference, keep papers in a library, and ask questions across them.
Sign up - it is free