Alexandre Variengien
3 papers · 2023–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
language model
(2)
mechanistic interpretability
(2)
attention head
(1)
causal intervention
(1)
causal analysis
(1)
prompt injection
(1)
reverse engineering
(1)
large language model
(1)
retrieval mechanism
(1)
mathematical ability
(1)
indirect object identification
(1)
internal oversight
(1)
modular processing
(1)
Papers
Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models
ICLR 2025
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
NeurIPS 2023
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small
ICLR 2023