@misc{wang2022interpretability,
  title={Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small},
  author={Kevin Wang and Alexandre Variengien and Arthur Conmy and Buck Shlegeris and Jacob Steinhardt},
  year={2022},
  eprint={2211.00593},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2211.00593}
}