| Imitating interactive intelligence J Abramson, A Ahuja, I Barr, A Brussee, F Carnevale, M Cassin, ... arXiv preprint arXiv:2012.05672, 2020 | 68 | 2020 |
| Goal misgeneralization: Why correct specifications aren't enough for correct goals R Shah, V Varma, R Kumar, M Phuong, V Krakovna, J Uesato, Z Kenton arXiv preprint arXiv:2210.01790, 2022 | 45 | 2022 |
| Explaining grokking through circuit efficiency V Varma, R Shah, Z Kenton, J Kramár, R Kumar arXiv preprint arXiv:2309.02390, 2023 | 29 | 2023 |
| Challenges with unsupervised LLM knowledge discovery S Farquhar, V Varma, Z Kenton, J Gasteiger, V Mikulik, R Shah arXiv preprint arXiv:2312.10029, 2023 | 7 | 2023 |
| Safe deep rl in 3d environments using human feedback M Rahtz, V Varma, R Kumar, Z Kenton, S Legg, J Leike arXiv preprint arXiv:2201.08102, 2022 | 7 | 2022 |
| Inter-device data transfer based on barcodes J Chien, RI Orton, G Weisz, V Varma US Patent 9,600,701, 2017 | 7 | 2017 |
| Improving dictionary learning with gated sparse autoencoders S Rajamanoharan, A Conmy, L Smith, T Lieberum, V Varma, J Kramár, ... arXiv preprint arXiv:2404.16014, 2024 | 6 | 2024 |
Zachary KentonGoogle DeepMindVerified email at google.com
