Towards Automated Circuit Discovery for Mechanistic Interpretability

Item #:

075280-0719

Details

DOI: https://doi.org/10.52202/075280-0719
Author(s): Arthur Conmy, Adrià Garriga-Alonso, Stefan Heimersheim, Aengus Lynch, Augustine Mavor-Parker
Pages: 16318-16352 (35 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/075280-0719
Author(s): Arthur Conmy, Adrià Garriga-Alonso, Stefan Heimersheim, Aengus Lynch, Augustine Mavor-Parker
Pages: 16318-16352 (35 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)