SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

Sparse coding with an overcomplete basis set: A strategy employed by v1?

Bruno A. Olshausen and David J. Field. 1997 · 1997

Earlier work this paper cites.

Xnli: Evaluating cross-lingual sentence representations

Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel R. Bowman, Holger Schwenk, and Veselin Stoyanov. 2018 · 2018

Earlier work this paper cites.

Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)

Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, et al. 2018 · 2018

Earlier work this paper cites.

Probing classifiers: Promises, shortcomings, and advances

Yonatan Belinkov. 2022 · 2022

Earlier work this paper cites.

Training language models to follow instructions with human feedback

Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022 · 2022

Earlier work this paper cites.

Multitask prompted training enables zero-shot task generalization

Victor Sanh, Albert Webson, Colin Raffel, Stephen H Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, et al. 2022 · 2022

Earlier work this paper cites.

Taking features out of superposition with sparse autoencoders

Lee Sharkey, Dan Braun, and Beren Millidge. 2022 · 2022

Earlier work this paper cites.

Finetuned language models are zero-shot learners

Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V Le. 2022 · 2022

Earlier work this paper cites.

Towards monosemanticity: Decomposing language models with dictionary learning

Trenton Bricken, Adly Templeton, Joshua Batson, Brian Chen, Adam Jermyn, Tom Conerly, Nicholas L Turner, Cem Anil, Carson Denison, Amanda Askell, Robert Lasenby, Yifan Wu, Shauna Kravec, Nicholas Schiefer, Tim Maxwell, Nicholas Joseph, Alex Tamkin, Karina Nguyen, Brayden McLean, Josiah E Burke, Tristan Hume, Shan Carter, Tom Henighan, and Chris Olah. 2023 · 2023

Earlier work this paper cites.

Do models really learn to follow instructions? an empirical study of instruction tuning

Po-Nien Kung and Nanyun Peng. 2023 · 2023

Earlier work this paper cites.

Neuronpedia: Interactive reference and tooling for analyzing neural networks

Johnny Lin. 2023 · 2023

Earlier work this paper cites.

Evaluating large language models on controlled generation tasks

Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu, Qian Hu, Rahul Gupta, John Wieting, Nanyun Peng, and Xuezhe Ma. 2023 · 2023

Cited alongside, same era.

Linear representations of sentiment in large language models

Original

Curt Tigges, Oskar John Hollinsworth, Atticus Geiger, and Neel Nanda. 2023 · 2023

Cited alongside, same era.

Instruction-following evaluation for large language models

Original

Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, and Le Hou. 2023 · 2023

Cited alongside, same era.

Representation engineering: A top-down approach to ai transparency

Original

Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, and Dan Hendrycks. 2023 · 2023

Cited alongside, same era.

Gemma scope: Open sparse autoencoders everywhere all at once on gemma 2

Original

Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, János Kramár, Anca Dragan, Rohin Shah, and Neel Nanda. 2024 · 2024

Later among the works it cites.

Instruction position matters in sequence generation with large language models

Yijin Liu, Xianfeng Zeng, Fandong Meng, and Jie Zhou. 2024 · 2024

Later among the works it cites.

(why) is my prompt getting worse? rethinking regression testing for evolving llm apis

Wanqin Ma, Chenyang Yang, and Christian Kästner. 2024 · 2024

Later among the works it cites.

The geometry of truth: Emergent linear structure in large language model representations of true/false datasets

Samuel Marks and Max Tegmark. 2024 · 2024

Later among the works it cites.

Jumping ahead: Improving reconstruction fidelity with jumprelu sparse autoencoders

Original