Transformerlens N Nanda, J Bloom URL: https://github. com/neelnanda-io/TransformerLens, 2022 | 48 | 2022 |
Transformerlens, 2022 N Nanda, J Bloom URL https://github. com/neelnanda-io/TransformerLens 17, 0 | 19 | |
Open source sparse autoencoders for all residual stream layers of GPT2 small J Bloom AI Alignment Forum, 24, 2024 | 12 | 2024 |
Saelens J Bloom, D Chanin GitHub repository, 30, 2024 | 9 | 2024 |
Interpreting attention layer outputs with sparse autoencoders C Kissane, R Krzyzanowski, JI Bloom, A Conmy, N Nanda arXiv preprint arXiv:2406.17759, 2024 | 8 | 2024 |
A is for absorption: Studying feature splitting and absorption in sparse autoencoders D Chanin, J Wilken-Smith, T Dulka, H Bhatnagar, J Bloom arXiv preprint arXiv:2409.14507, 2024 | 4 | 2024 |
Stitching Sparse Autoencoders of Different Sizes P Leask, B Bussmann, JI Bloom, C Tigges, N Al Moubayed, N Nanda NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning, 0 | 1 | |