This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Transformer Circuits
Edit
History
Subscribe
Discussion
(1)
Help improve this page
Edit
History
Subscribe
Discussion
(1)
Help improve this page
Transformer Circuits
Random Tag
Contributors
Posts tagged
Transformer Circuits
Most Relevant
3
33
Finding Neurons in a Haystack: Case Studies with Sparse Probing
Ω
wesg
,
Neel Nanda
1y
Ω
5
2
112
Interpreting OpenAI's Whisper
EllenaR
8mo
10
2
104
200 Concrete Open Problems in Mechanistic Interpretability: Introduction
Ω
Neel Nanda
1y
Ω
0
2
68
Finding Sparse Linear Connections between Features in LLMs
Ω
Logan Riggs
,
Sam Mitchell
,
Eccentricity
5mo
Ω
5
2
50
How to Think About Activation Patching
Ω
Neel Nanda
1y
Ω
5
2
44
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla
Ω
Neel Nanda
,
Tom Lieberum
,
Matthew Rahtz
,
János Kramár
,
Geoffrey Irving
,
Rohin Shah
,
Vlad Mikulik
10mo
Ω
3
2
36
Paper Walkthrough: Automated Circuit Discovery with Arthur Conmy
Ω
Neel Nanda
9mo
Ω
1
2
34
200 COP in MI: Exploring Polysemanticity and Superposition
Ω
Neel Nanda
1y
Ω
6
2
33
200 COP in MI: Interpreting Algorithmic Problems
Ω
Neel Nanda
1y
Ω
2
2
30
A Walkthrough of Interpretability in the Wild (w/ authors Kevin Wang, Arthur Conmy & Alexandre Variengien)
Ω
Neel Nanda
2y
Ω
15
2
20
A Walkthrough of In-Context Learning and Induction Heads (w/ Charles Frye) Part 1 of 2
Ω
Neel Nanda
1y
Ω
0
2
16
200 COP in MI: Looking for Circuits in the Wild
Ω
Neel Nanda
1y
Ω
5
2
16
Understanding the tensor product formulation in Transformer Circuits
Tom Lieberum
2y
2
2
16
200 COP in MI: Analysing Training Dynamics
Ω
Neel Nanda
1y
Ω
0
2
13
200 COP in MI: Techniques, Tooling and Automation
Ω
Neel Nanda
1y
Ω
0