Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders

Item #:

079017-0024

Details

DOI: https://doi.org/10.52202/079017-0024
Author(s): Arthur Conmy, János Kramár, Tom Lieberum, Neel Nanda, Senthooran Rajamanoharan, Rohin Shah, Lewis Smith, Vikrant Varma
Pages: 775-818 (44 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-0024
Author(s): Arthur Conmy, János Kramár, Tom Lieberum, Neel Nanda, Senthooran Rajamanoharan, Rohin Shah, Lewis Smith, Vikrant Varma
Pages: 775-818 (44 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)