Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Learning efficient linear codes for natural images: the roles of sparseness, overcompleteness, and statistical independence

Bruno A. Olshausen and David J. Field · 1996

Earlier work this paper cites.

Scaling laws for neural language models

Original

Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei · 2001

Earlier work this paper cites.

Efficient estimation of word representations in vector space

Original

Tomás Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean · 2013

Earlier work this paper cites.

Deep residual learning for image recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016

Earlier work this paper cites.

Understanding intermediate layers using linear classifier probes

Guillaume Alain and Yoshua Bengio · 2017

Earlier work this paper cites.

Linear algebraic structure of word senses, with applications to polysemy

Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, and Andrej Risteski · 2018

Earlier work this paper cites.

Jumprelu: A retrofit defense strategy for adversarial attacks

N. Benjamin Erichson, Zhewei Yao, and Michael W. Mahoney · 2020

Earlier work this paper cites.

Zoom in: An introduction to circuits

Chris Olah, Nick Cammarata, Ludwig Schubert, Gabriel Goh, Michael Petrov, and Shan Carter · 2020

Earlier work this paper cites.

Knowledge neurons in pretrained transformers

Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, and Furu Wei · 2022

Earlier work this paper cites.

Softmax linear units

Nelson Elhage, Tristan Hume, Catherine Olsson, Neel Nanda, Tom Henighan, Scott Johnston, Sheer ElShowk, Nicholas Joseph, Nova DasSarma, Ben Mann, Danny Hernandez, Amanda Askell, Kamal Ndousse, Andy Jones, Dawn Drain, Anna Chen, Yuntao Bai, Deep Ganguli, Liane Lovitt, Zac Hatfield-Dodds, Jackson Kernion, Tom Conerly, Shauna Kravec, Stanislav Fort, Saurav Kadavath, Josh Jacobson, Eli Tran-Johnson, Jared Kaplan, Jack Clark, Tom Brown, Sam McCandlish, Dario Amodei, and Christopher Olah · 2022

Earlier work this paper cites.

Toy models of superposition

Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby, Dawn Drain, Carol Chen, Roger Grosse, Sam McCandlish, Jared Kaplan, Dario Amodei, Martin Wattenberg, and Christopher Olah · 2022

Earlier work this paper cites.

Training compute-optimal large language models

Original

Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, Tom Hennigan, Eric Noland, Katie Millican, George van den Driessche, Bogdan Damoc, Aurelia Guy, Simon Osindero, Karen Simonyan, Erich Elsen, Jack W. Rae, Oriol Vinyals, and Laurent Sifre · 2022

Earlier work this paper cites.

Language models can explain neurons in language models

Steven Bills, Nick Cammarata, Dan Mossing, Henk Tillman, Leo Gao, Gabriel Goh, Ilya Sutskever, Jan Leike, Jeff Wu, and William Saunders · 2023

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, Nick Turner, Cem Anil, Carson Denison, Amanda Askell, Robert Lasenby, Yifan Wu, Shauna Kravec, Nicholas Schiefer, Tim Maxwell, Nicholas Joseph, Zac Hatfield-Dodds, Alex Tamkin, Karina Nguyen, Brayden McLean, Josiah E Burke, Tristan Hume, Shan Carter, Tom Henighan, and Christopher Olah · 2023

Earlier work this paper cites.

Privileged bases in the transformer residual stream

Nelson Elhage, Robert Lasenby, and Christopher Olah · 2023

Earlier work this paper cites.

Finding neurons in a haystack: Case studies with sparse probing

Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, and Dimitris Bertsimas · 2023

Cited alongside, same era.

SlimPajama: A 627B token cleaned and deduplicated version of RedPajama

Daria Soboleva, Faisal Al-Khateeb, Robert Myers, Jacob R Steeves, Joel Hestness, and Nolan Dey · 2023

Cited alongside, same era.

L-eval: Instituting standardized evaluation for long context language models

Chenxin An, Shansan Gong, Ming Zhong, Xingjian Zhao, Mukai Li, Jun Zhang, Lingpeng Kong, and Xipeng Qiu · 2024

Cited alongside, same era.

Sparse autoencoders find composed features in small toy models

Evan Anders, Clement Neo, Jason Hoelscher-Obermaier, and Jessica N. Howard · 2024

Cited alongside, same era.

Using dictionary learning features as classifiers

Trenton Bricken, Jonathan Marcus, Siddharth Mishra-Sharma, Meg Tong, Ethan Perez, Mrinank Sharma, Kelley Rivoire, Thomas Henighan, and Adam Jermyn · 2024

Cited alongside, same era.

Saes (usually) transfer between base and chat models

Connor Kissane, Robert Krzyzanowski, Arthur Conmy, and Neel Nanda · 2024

Closest in time.

Sparse autoencoders reveal universal feature spaces across large language models

Original

Michael Lan, Philip Torr, Austin Meek, Ashkan Khakzar, David Krueger, and Fazl Barez · 2024

Closest in time.

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

Closest in time.

Sparse feature circuits: Discovering and editing interpretable causal graphs in language models

Original

Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, and Aaron Mueller · 2024

Closest in time.

Gemma: Open models based on gemini research and technology