Towards Automated Circuit Discovery for Mechanistic Interpretability
arxiv.org · 7,455 words · saved by 2 readers
N/A
Towards Automated Circuit Discovery for Mechanistic Interpretability Arthur Conmy∗ Augustine N. Mavor-Parker∗ Aengus Lynch∗ Stefan Heimersheim Independent UCL UCL University of Cambridge arXiv:2304.14997v4 [cs.LG] 28 Oct 2023 Adrià Garriga-Alonso∗…
saved by
related reading
- Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
- Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decompositionarxiv.org
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- Transformer Circuits Threadtransformer-circuits.pub
- In-context Learning and Induction Headstransformer-circuits.pub
- On the Biology of a Large Language Modeltransformer-circuits.pub
- An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
- An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
- Softmax Linear Unitstransformer-circuits.pub
- Mechanistic Interpretability: Circuits, Induction Headsmbrenndoerfer.com