@article{enhancingneuralnetworkinterpretability1, title = {Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders}, author = {Luke Marks and Alasdair Paren and David Krueger and Fazl Barez}, year = {2024}, eprint = {2411.01220}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.01220v2}, }