LESSWRONG
Wikitags
LW

1

Transformer Circuits

1

This page is a stub.

Posts tagged Transformer Circuits

3

33Finding Neurons in a Haystack: Case Studies with Sparse Probing

wesg, Neel Nanda

2y

6

2

135An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2

9mo

16

2

116Interpreting OpenAI's Whisper

2y

13

2

106200 Concrete Open Problems in Mechanistic Interpretability: Introduction

2y

0

2

70Finding Sparse Linear Connections between Features in LLMs

Logan Riggs, Sam Mitchell, Adam Kaufman

1y

5

2

50How to Think About Activation Patching

2y

5

2

44Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

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

2y

3

2

36Paper Walkthrough: Automated Circuit Discovery with Arthur Conmy

2y

1

2

34200 COP in MI: Exploring Polysemanticity and Superposition

2y

6

2

33200 COP in MI: Interpreting Algorithmic Problems

2y

2

2

30A Walkthrough of Interpretability in the Wild (w/ authors Kevin Wang, Arthur Conmy & Alexandre Variengien)

2y

15

2

20A Walkthrough of In-Context Learning and Induction Heads (w/ Charles Frye) Part 1 of 2

2y

0

2

16Sleep peacefully: no hidden reasoning detected in LLMs. Well, at least in small ones.

Ilia Shirokov, Ilya Nachevsky

15d

2

2

16Understanding the tensor product formulation in Transformer Circuits

3y

2

2

16200 COP in MI: Analysing Training Dynamics

2y

0