LESSWRONGTags
LW

Apollo Research (org)

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Apollo Research (org)

Contributors

Posts tagged Apollo Research (org)

2

221SAE feature geometry is outside the superposition hypothesis

5mo

17

2

215Announcing Apollo Research

Marius Hobbhahn, beren, Lee Sharkey, Lucius Bushnaq, Dan Braun, Mikita Balesni, Jérémy Scheurer

1y

11

2

161You can remove GPT2’s LayerNorm by fine-tuning for an hour

3mo

11

2

117A List of 45+ Mech Interp Project Ideas from Apollo Research’s Interpretability Team

Lee Sharkey, Lucius Bushnaq, Dan Braun, StefanHex, Nicholas Goldowsky-Dill

4mo

18

2

105The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks

Lucius Bushnaq, jake_mendel, Dan Braun, StefanHex, Nicholas Goldowsky-Dill, Kaarel, Avery, Joern Stoehler, debrevitatevitae, Magdalena Wache, Marius Hobbhahn

6mo

4

2

103Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs

L Rudolf L, bilalchughtai, jan betley, kaivu, Jérémy Scheurer, Mikita Balesni, AlexMeinke, Owain_Evans, Marius Hobbhahn

4mo

28

2

94Sparsify: A mechanistic interpretability research agenda

8mo

22

2

93Apollo Research 1-year update

Marius Hobbhahn, Lee Sharkey, Lucius Bushnaq, Dan Braun, Mikita Balesni, Jérémy Scheurer, Nicholas Goldowsky-Dill, StefanHex, jake_mendel, AlexMeinke, rusheb

6mo

0

2

71We need a Science of Evals

Marius Hobbhahn, Jérémy Scheurer

10mo

13

2

65An Opinionated Evals Reading List

Marius Hobbhahn, Jérémy Scheurer

1mo

0

2

64[Interim research report] Activation plateaus & sensitive directions in GPT2

StefanHex, jake_mendel

5mo

2

2

64Understanding strategic deception and deceptive alignment

Marius Hobbhahn, Mikita Balesni, Jérémy Scheurer, Dan Braun

1y

16

2

57Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

Dan Braun, Jordan Taylor, Nicholas Goldowsky-Dill, Lee Sharkey

6mo

10

2

54Theories of Change for AI Auditing

Lee Sharkey, beren, Marius Hobbhahn

1y

0

2

50A starter guide for evals

Marius Hobbhahn, Jérémy Scheurer, Mikita Balesni, rusheb, AlexMeinke

10mo

2