Fetching the paper…
Reading the bibliography…
Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque.
Adam: A method for stochastic optimization
Diederik P Kingma and Jimmy Ba. 2014 · 2014
Earlier work this paper cites.
" why should i trust you?" explaining the predictions of any classifier
Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016 · 2016
Earlier work this paper cites.
Understanding black-box predictions via influence functions
Pang Wei Koh and Percy Liang. 2017 · 2017
Earlier work this paper cites.
A unified approach to interpreting model predictions
Scott M Lundberg and Su-In Lee. 2017 · 2017
Earlier work this paper cites.
Language models are few-shot learners
Tom B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020 · 2020
Earlier work this paper cites.
Curve detectors
Nick Cammarata, Gabriel Goh, Shan Carter, Ludwig Schubert, Michael Petrov, and Chris Olah. 2020 · 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. 2020a · 2020
Earlier work this paper cites.
Naturally occurring equivariance in neural networks
Chris Olah, Nick Cammarata, Chelsea Voss, Ludwig Schubert, and Gabriel Goh. 2020b · 2020
Earlier work this paper cites.
Prevalence of neural collapse during the terminal phase of deep learning training
Vardan Papyan, XY Han, and David L Donoho. 2020 · 2020
Earlier work this paper cites.
High-low frequency detectors
Ludwig Schubert, Chelsea Voss, Nick Cammarata, Gabriel Goh, and Chris Olah. 2021 · 2020
Earlier work this paper cites.
A mathematical framework for transformer circuits
Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Nova DasSarma, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amodei, Tom Brown, Jack Clark, Jared Kaplan, Sam McCandlish, and Chris Olah. 2021 · 2021
Earlier work this paper cites.
Transformer feed-forward layers are key-value memories
Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. 2021 · 2021
Earlier work this paper cites.
Lora: Low-rank adaptation of large language models
Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021 · 2021
Earlier work this paper cites.
Deep double descent: Where bigger models and more data hurt
Preetum Nakkiran, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak, and Ilya Sutskever. 2021 · 2021
Earlier work this paper cites.
Causal scrubbing, a method for rigorously testing interpretability hypotheses
Lawrence Chan, Adrià Garriga-Alonso, Nicholas Goldwosky-Dill, Ryan Greenblatt, Jenny Nitishinskaya, Ansh Radhakrishnan, Buck Shlegeris, and Nate Thomas. 2022 · 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 · 2022
Earlier work this paper cites.
Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space
Mor Geva, Avi Caciularu, Kevin Ro Wang, and Yoav Goldberg. 2022 · 2022
Earlier work this paper cites.
Engineering monosemanticity in toy models
Adam S Jermyn, Nicholas Schiefer, and Evan Hubinger. 2022 · 2022
Earlier work this paper cites.
Emergent world representations: Exploring a sequence model trained on a synthetic task
Kenneth Li, Aspen K Hopkins, David Bau, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. 2022 · 2022
Earlier work this paper cites.
Locating and editing factual associations in gpt
Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022 · 2022
Earlier work this paper cites.
In-context learning and induction heads
Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Scott Johnston, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amodei, Tom Brown, Jack Clark, Jared Kaplan, Sam McCandlish, and Chris Olah. 2022 · 2022
Earlier work this paper cites.
Grokking: Generalization beyond overfitting on small algorithmic datasets
Alethea Power, Yuri Burda, Harri Edwards, Igor Babuschkin, and Vedant Misra. 2022 · 2022
Earlier work this paper cites.
Polysemanticity and capacity in neural networks
Adam Scherlis, Kshitij Sachan, Adam S Jermyn, Joe Benton, and Buck Shlegeris. 2022 · 2022
Earlier work this paper cites.
The slingshot mechanism: An empirical study of adaptive optimizers and the Grokking Phenomenon
Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, and Joshua M. Susskind. 2022 · 2022
Earlier work this paper cites.
Interpretability in the wild: a circuit for indirect object identification in gpt-2 small
Kevin Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt. 2022 · 2022
Earlier work this paper cites.
Emergent abilities of large language models
Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. 2022 · 2022
Cited alongside, same era.
Introducing claude
AnthropicAI. 2023 · 2023
Cited alongside, same era.
The internal state of an llm knows when its lying
Amos Azaria and Tom Mitchell. 2023 · 2023
Cited alongside, same era.
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 · 2023
Cited alongside, same era.
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 · 2023
Cited alongside, same era.
Mass-editing memory in a transformer
Kevin Meng, Arnab Sen Sharma, Alex J Andonian, Yonatan Belinkov, and David Bau. 2023 · 2023
Later among the works it cites.
A tale of two circuits: Grokking as competition of sparse and dense subnetworks
William Merrill, Nikolaos Tsilivis, and Aman Shukla. 2023 · 2023
Later among the works it cites.
Grokking modular arithmetic can be explained by margin maximization
Mohamad Amin Mohamadi, Zhiyuan Li, Lei Wu, and Danica Sutherland. 2023 · 2023
Later among the works it cites.
OpenAI. 2023 · 2023
Later among the works it cites.
A mechanistic interpretation of arithmetic reasoning in language models using causal mediation analysis
Alessandro Stolfo, Yonatan Belinkov, and Mrinmaya Sachan. 2023 · 2023
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
James Campbell, Richard Ren, and Phillip Guo. 2023 · 2023
Cited alongside, same era.
Do androids know they’re only dreaming of electric sheep?
Sky CH-Wang, Benjamin Van Durme, Jason Eisner, and Chris Kedzie. 2023 · 2023
Cited alongside, same era.
Neural networks learn representation theory: Reverse engineering how networks perform group operations
Bilal Chughtai, Lawrence Chan, and Neel Nanda. 2023 · 2023
Cited alongside, same era.
Evaluating the ripple effects of knowledge editing in language models
Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, and Mor Geva. 2023 · 2023
Cited alongside, same era.
Unifying grokking and double descent
Xander Davies, Lauro Langosco, and David Krueger. 2023 · 2023
Cited alongside, same era.
Darshil Doshi, Aritra Das, Tianyu He, and Andrey Gromov. 2023 · 2023
Cited alongside, same era.
Dan Friedman, Alexander Wettig, and Danqi Chen. 2023 · 2023
Cited alongside, same era.
Alex Tamkin, Amanda Askell, Liane Lovitt, Esin Durmus, Nicholas Joseph, Shauna Kravec, Karina Nguyen, Jared Kaplan, and Deep Ganguli. 2023 · 2023
Later among the works it cites.
Gemini: a family of highly capable multimodal models
Gemini Team, Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, et al. 2023 · 2023
Later among the works it cites.
Function vectors in large language models
Eric Todd, Millicent L Li, Arnab Sen Sharma, Aaron Mueller, Byron C Wallace, and David Bau. 2023 · 2023
Later among the works it cites.
Llama 2: Open foundation and fine-tuned chat models
Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023 · 2023
Later among the works it cites.
Activation addition: Steering language models without optimization
Alex Turner, Lisa Thiergart, David Udell, Gavin Leech, Ulisse Mini, and Monte MacDiarmid. 2023 · 2023
Later among the works it cites.
Bias a-head? analyzing bias in transformer-based language model attention heads
Yi Yang, Hanyu Duan, Ahmed Abbasi, John P Lalor, and Kar Yan Tam. 2023 · 2023
Later among the works it cites.
Explainability for large language models: A survey
Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, and Mengnan Du. 2023 · 2023
Later among the works it cites.
The clock and the pizza: Two stories in mechanistic explanation of neural networks
Ziqian Zhong, Ziming Liu, Max Tegmark, and Jacob Andreas. 2023 · 2023
Later among the works it cites.
Representation engineering: A top-down approach to ai transparency
Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, et al. 2023 · 2023
Later among the works it cites.
Finding alignments between interpretable causal variables and distributed neural representations
Atticus Geiger, Zhengxuan Wu, Christopher Potts, Thomas Icard, and Noah Goodman. 2024 · 2024
Closest in time.
Exploring concept depth: How large language models acquire knowledge at different layers?
Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, and Yongfeng Zhang. 2024 · 2024
Closest in time.
How large language models encode context knowledge? a layer-wise probing study
Tianjie Ju, Weiwei Sun, Wei Du, Xinwei Yuan, Zhaochun Ren, and Gongshen Liu. 2024 · 2024
Closest in time.
What causes polysemanticity? an alternative origin story of mixed selectivity from incidental causes
Victor Lecomte, Kushal Thaman, Rylan Schaeffer, Naomi Bashkansky, Trevor Chow, and Sanmi Koyejo. 2024 · 2024
Closest in time.
A mechanistic understanding of alignment algorithms: A case study on dpo and toxicity
Andrew Lee, Xiaoyan Bai, Itamar Pres, Martin Wattenberg, Jonathan K Kummerfeld, and Rada Mihalcea. 2024 · 2024
Closest in time.
Inference-time intervention: Eliciting truthful answers from a language model
Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. 2024 · 2024
Closest in time.
From understanding to utilization: A survey on explainability for large language models
Haoyan Luo and Lucia Specia. 2024 · 2024
Closest in time.
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey, Dan Braun, and beren. 2022 · 2024
Closest in time.
Localizing paragraph memorization in language models
Niklas Stoehr, Mitchell Gordon, Chiyuan Zhang, and Owen Lewis. 2024 · 2024
Closest in time.
Critical data size of language models from a grokking perspective
Xuekai Zhu, Yao Fu, Bowen Zhou, and Zhouhan Lin. 2024 · 2024
Closest in time.