| Active estimation for jump Markov linear systems L Blackmore, S Rajamanoharan, BC Williams IEEE Transactions on Automatic Control 53 (10), 2223-2236, 2008 | 110 | 2008 |
| Gemma scope: Open sparse autoencoders everywhere all at once on gemma 2 T Lieberum, S Rajamanoharan, A Conmy, L Smith, N Sonnerat, V Varma, ... arXiv preprint arXiv:2408.05147, 2024 | 62 | 2024 |
| 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 | 47 | 2024 |
| Jumping ahead: Improving reconstruction fidelity with jumprelu sparse autoencoders S Rajamanoharan, T Lieberum, N Sonnerat, A Conmy, V Varma, J Kramár, ... arXiv preprint arXiv:2407.14435, 2024 | 35 | 2024 |
| Fact finding: Attempting to reverse-engineer factual recall on the neuron level N Nanda, S Rajamanoharan, J Kramar, R Shah Alignment Forum, 6, 2023 | 17 | 2023 |
| Fact finding: Attempting to reverse-engineer factual recall on the neuron level, Dec 2023 N Nanda, S Rajamanoharan, J Kramár, R Shah URL https://www. alignmentforum. org/posts/iGuwZTHWb6DFY3sKB/fact-finding …, 0 | 16 | |
| Cusps on cosmic superstrings with junctions AC Davis, W Nelson, S Rajamanoharan, M Sakellariadou Journal of Cosmology and Astroparticle Physics 2008 (11), 022, 2008 | 12 | 2008 |
| Active estimation for switching linear dynamic systems L Blackmore, S Rajamanoharan, BC Williams Proceedings of the 45th IEEE Conference on Decision and Control, 137-144, 2006 | 12 | 2006 |
| Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models J Ferrando, O Obeso, S Rajamanoharan, N Nanda arXiv preprint arXiv:2411.14257, 2024 | 5 | 2024 |
| Improving sparse decomposition of language model activations with gated sparse autoencoders S Rajamanoharan, A Conmy, L Smith, T Lieberum, V Varma, J Kramar, ... Advances in Neural Information Processing Systems 37, 775-818, 2025 | 2 | 2025 |
| Bogomol'nyi bounds for gravitational cosmic strings AC Davis, S Rajamanoharan Journal of High Energy Physics 2009 (01), 027, 2009 | 2 | 2009 |
| Are Sparse Autoencoders Useful? A Case Study in Sparse Probing S Kantamneni, J Engels, S Rajamanoharan, M Tegmark, N Nanda arXiv preprint arXiv:2502.16681, 2025 | | 2025 |
| Cosmic superstrings and bimetric gravity S Rajamanoharan University of Cambridge, 2012 | | 2012 |
| LLM Neurosurgeon: Targeted Knowledge Removal in LLMs using Sparse Autoencoders D Zhou, K Patil, Y Sun, S Rajamanoharan | | |
Neel NandaMechanistic Interpretability Team Lead, Google DeepMindVahvistettu sähköpostiosoite verkkotunnuksessa deepmind.com