AI ALIGNMENT FORUMTags
AF

Transformer Circuits

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Transformer Circuits

Contributors

Posts tagged Transformer Circuits

1

17Finding Neurons in a Haystack: Case Studies with Sparse Probing

Wes Gurnee, Neel Nanda

7mo

0

1

37200 Concrete Open Problems in Mechanistic Interpretability: Introduction

1y

0

1

21Finding Sparse Linear Connections between Features in LLMs

Logan Riggs Smith, Sam Mitchell, Adam Kaufman

2d

2

2

22How to Think About Activation Patching

6mo

3

2

23Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

Neel Nanda, Tom Lieberum, Matthew Rahtz, János Kramár, Geoffrey Irving, Rohin Shah, Vladimir Mikulik

5mo

0

2

16Paper Walkthrough: Automated Circuit Discovery with Arthur Conmy

3mo

1

1

17200 COP in MI: Interpreting Algorithmic Problems

1y

0

1

16A Walkthrough of Interpretability in the Wild (w/ authors Kevin Wang, Arthur Conmy & Alexandre Variengien)

1y

15

1

12200 COP in MI: Exploring Polysemanticity and Superposition

1y

0

1

11A Walkthrough of In-Context Learning and Induction Heads (w/ Charles Frye) Part 1 of 2

1y

0

1

11200 COP in MI: Analysing Training Dynamics

1y

0

1

8200 COP in MI: Looking for Circuits in the Wild

1y

3

1

7200 COP in MI: Techniques, Tooling and Automation

1y

0

0

28An Interpretability Illusion for Activation Patching of Arbitrary Subspaces

Georg Lange, Alex Makelov, Neel Nanda

3mo

0

0

29Polysemantic Attention Head in a 4-Layer Transformer

Jett Janiak, cmathw, Stefan Heimersheim

1mo

0