|
|
| | Towards Monosemanticity: Decomposing Language Models with Dictionary Learning (transformer-circuits.pub) | | 72 points by goodmachine on Oct 6, 2023 | past | 5 comments | |
| | In-Context Learning and Induction Heads (transformer-circuits.pub) | | 2 points by ZeljkoS on Sept 6, 2023 | past | |
| | Toy Models of Superposition (2022) (transformer-circuits.pub) | | 46 points by ZeljkoS on Aug 21, 2023 | past | 4 comments | |
| | Anthropic’s Transformer Circuits Publication (transformer-circuits.pub) | | 2 points by tim_sw on May 24, 2023 | 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
|
