@article{sparsefeaturecircuitsdiscoveringand,
  title = {Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models},
  author = {Samuel Marks and Can Rager and Eric J. Michaud and Yonatan Belinkov and David Bau and Aaron Mueller},
  year = {2024},
  eprint = {2403.19647},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.19647v3},
}