@article{towardsprincipledevaluationsofsparse,
  title = {Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control},
  author = {Aleksandar Makelov and George Lange and Neel Nanda},
  year = {2024},
  eprint = {2405.08366},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.08366v3},
}