Alexandre Variengien

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 8

Top Topics

Language Modelling

Object Identification

Test Collection

Top Venues

Publications

Diego Dorn, Alexandre Variengien, Charbel-Raphaël Ségerie, Vincent Corruble
BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards. CoRR (2024)
Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, Jacob Steinhardt
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small. ICLR (2023)
Michael Hanna, Ollie Liu, Alexandre Variengien
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. CoRR (2023)
Michael Hanna, Ollie Liu, Alexandre Variengien
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. NeurIPS (2023)
Alexandre Variengien, Eric Winsor
Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models. CoRR (2023)
Kevin Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, Jacob Steinhardt
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small. CoRR (2022)
Alexandre Variengien, Stefano Nichele, Tom Eivind Glover, Sidney Pontes-Filho
Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent. CoRR (2021)
Alexandre Variengien, Xavier Hinaut
A journey in ESN and LSTM visualisations on a language task. CoRR (2020)