Hacker News new | past | comments | ask | show | jobs | submit | from login

Reflections on Qualitative Research (transformer-circuits.pub) 54 points by martingalex2 13 days ago | past | 3 comments In-Context Learning and Induction Heads (transformer-circuits.pub) 2 points by throwup238 3 months ago | past Circuits Updates – January 2024 (transformer-circuits.pub) 1 point by 1wheel 3 months ago | past Towards Monosemanticity: Decomposing Language Models with Dictionary Learning (transformer-circuits.pub) 72 points by goodmachine 7 months ago | past | 5 comments In-Context Learning and Induction Heads (transformer-circuits.pub) 2 points by ZeljkoS 8 months ago | past Toy Models of Superposition (2022) (transformer-circuits.pub) 46 points by ZeljkoS 8 months ago | past | 4 comments Anthropic’s Transformer Circuits Publication (transformer-circuits.pub) 2 points by tim_sw 11 months ago | past A Mathematical Framework for Transformer Circuits (transformer-circuits.pub) 1 point by ZeljkoS on Feb 7, 2023 | past Superposition, Memorization, and Double Descent (transformer-circuits.pub) 69 points by lamename on Jan 5, 2023 | past | 7 comments Toy Models of Superposition (transformer-circuits.pub) 2 points by yyyk on Sept 17, 2022 | past Toy Models of Superposition [in Neural Networks] (transformer-circuits.pub) 1 point by escape_goat on Sept 16, 2022 | past Toy Models of Superposition (transformer-circuits.pub) 6 points by ctoth on Sept 14, 2022 | past Can we reverse engineer transformer models into human-understandable programs? (transformer-circuits.pub) 33 points by apsec112 on Dec 22, 2021 | past | 4 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: