Sparse Autoencoders Find Highly Interpretable Features in Language Models

15 September 2023

Papers citing "Sparse Autoencoders Find Highly Interpretable Features in Language Models"

7 / 57 papers shown

Title
Black-Box Access is Insufficient for Rigorous AI Audits Stephen Casper Carson Ezell Charlotte Siegmann Noam Kolt Taylor Lynn Curtis ... Michael Gerovitch David Bau Max Tegmark David M. Krueger Dylan Hadfield-Menell AAML 8 75 0 25 Jan 2024
Forbidden Facts: An Investigation of Competing Objectives in Llama-2 Tony T. Wang Miles Wang Kaivu Hariharan Nir Shavit 8 2 0 14 Dec 2023
Towards Best Practices of Activation Patching in Language Models: Metrics and Methods Fred Zhang Neel Nanda LLMSV 10 95 0 27 Sep 2023
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Kevin Wang Alexandre Variengien Arthur Conmy Buck Shlegeris Jacob Steinhardt 207 486 0 01 Nov 2022
Toy Models of Superposition Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer T. Henighan ... Sam McCandlish Jared Kaplan Dario Amodei Martin Wattenberg C. Olah AAML MILM 117 314 0 21 Sep 2022
Linear Adversarial Concept Erasure Shauli Ravfogel Michael Twiton Yoav Goldberg Ryan Cotterell KELM 62 56 0 28 Jan 2022
The Pile: An 800GB Dataset of Diverse Text for Language Modeling Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe ... Horace He Anish Thite Noa Nabeshima Shawn Presser Connor Leahy AIMat 236 1,508 0 31 Dec 2020