@misc{power2022grokking, title={Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets}, author={Alethea Power and Yuri Burda and Harri Edwards and Igor Babuschkin and Vedant Misra}, year={2022}, eprint={2201.02177}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2201.02177} }