✳flâneur — a map of the web's best reading
Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level (Post 1) — AI Alignment Forum
alignmentforum.org · 10,186 words · saved by 1 readers
If you've come here via 3Blue1Brown, hi! If want to learn more about interpreting neural networks in general, here are some resources you might find…
x Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level (Post 1) — AI Alignment Forum Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level Interpretability (ML & AI) Rationality Frontpage 49 Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level (Post 1) by Neel Nanda , Senthooran Rajamanoharan , János Kramár , Rohin Shah 23rd Dec 2023 26 min read 12 49 If you've come here via 3Blue1Brown , hi! If want to learn more about interpreting neural networks in general, here are some resources you might find useful: My getti
Explore this link on the map →saved by
related reading
- Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level (Post 1) — LessWronglesswrong.com
- An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
- Toy Models of Superpositiontransformer-circuits.pub
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- Fact Finding: Simplifying the Circuit (Post 2) — LessWronglesswrong.com
- On the Biology of a Large Language Modeltransformer-circuits.pub
- Zoom In: An Introduction to Circuitsdistill.pub
- An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
- Transformer Circuits Threadtransformer-circuits.pub
- Interpretability Dreamstransformer-circuits.pub
- Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
- Circuits Updates - January 2024transformer-circuits.pub