Fetching the paper…
Reading the bibliography…
Recent work in mechanistic interpretability has shown that behaviors in language models can be successfully reverse-engineered through circuit analysis.
Learning long-range spatial dependencies with horizontal gated recurrent units
Drew Linsley, Junkyung Kim, Vijay Veerabadran, Charles Windolf, and Thomas Serre · 2018
Earlier work this paper cites.
A multiscale visualization of attention in the transformer model
Jesse Vig · 2019
Earlier work this paper cites.
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
Elena Voita, David Talbot, Fedor Moiseev, Rico Sennrich, and Ivan Titov · 2019
Earlier work this paper cites.
Attention is not only a weight: Analyzing transformers with vector norms
Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, and Kentaro Inui · 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.
Investigating transferability in pretrained language models
Alex Tamkin, Trisha Singh, Davide Giovanardi, and Noah Goodman · 2020
Earlier work this paper cites.
Investigating Gender Bias in Language Models Using Causal Mediation Analysis
Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber · 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
Earlier work this paper cites.
Transformer feed-forward layers are key-value memories
Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy · 2021
Cited alongside, same era.
What changed? investigating debiasing methods using causal mediation analysis
Sullam Jeoung and Jana Diesner · 2022
Cited alongside, same era.
Mass-editing memory in a transformer
Kevin Meng, Arnab Sen Sharma, Alex J Andonian, Yonatan Belinkov, and David Bau · 2022
Cited alongside, same era.
Transformerlens, 2022
Neel Nanda and Joseph Bloom · 2022
Cited alongside, same era.
Progress measures for grokking via mechanistic interpretability
Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, and Jacob Steinhardt · 2022
Cited alongside, same era.
In-context learning and induction heads, 2022
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
Dissecting recall of factual associations in auto-regressive language models, 2023
Mor Geva, Jasmijn Bastings, Katja Filippova, and Amir Globerson · 2023
Closest in time.
Localizing model behavior with path patching
Nicholas Goldowsky-Dill, Chris MacLeod, Lucas Sato, and Aryaman Arora · 2023
Closest in time.
Finding neurons in a haystack: Case studies with sparse probing
Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, and Dimitris Bertsimas · 2023
Closest in time.
How does gpt-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model, 2023
Michael Hanna, Ollie Liu, and Alexandre Variengien · 2023
Closest in time.
Generative models as a complex systems science: How can we make sense of large language model behavior?
Ari Holtzman, Peter West, and Luke Zettlemoyer · 2023
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Interpretability in the Wild: A Circuit for Indirect Object Identification in GPT-2 Small
Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt · 2022
Cited alongside, same era.
Towards automated circuit discovery for mechanistic interpretability, 2023
Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch, Stefan Heimersheim, and Adrià Garriga-Alonso · 2023
Cited alongside, same era.
Direct and indirect effects. 2001in: Proceedings of the seventeenth conference on uncertainty in artificial intelligence
J Pearl
Cited in the paper.
Language models are unsupervised multitask learners
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al
Cited in the paper.
Closest in time.
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
Daphne Ippolito and Chris Callison-Burch · 2023
Closest in time.
Does circuit analysis interpretability scale? evidence from multiple choice capabilities in chinchilla, 2023
Tom Lieberum, Matthew Rahtz, János Kramár, Neel Nanda, Geoffrey Irving, Rohin Shah, and Vladimir Mikulik · 2023
Closest in time.
Language models implement simple word2vec-style vector arithmetic, 2023
Jack Merullo, Carsten Eickhoff, and Ellie Pavlick · 2023
Closest in time.