RSS

Arthur Conmy

Karma: 1,498

Intepretability

Views my own

SAEBench: A Com­pre­hen­sive Bench­mark for Sparse Autoencoders

Can, Adam Karvonen, Johnny Lin, Curt Tigges, Joseph Bloom, chanind, Yeu-Tong Lau, Eoin Farrell, Arthur Conmy, CallumMcDougall, Kola Ayonrinde, Matthew Wearden, Sam Marks and Neel Nanda
11 Dec 2024 6:30 UTC
80 points
6 comments2 min readLW link
(www.neuronpedia.org)

Evolu­tion­ary prompt op­ti­miza­tion for SAE fea­ture visualization

neverix, Daniel Tan, Dmitrii Kharlapenko, Neel Nanda and Arthur Conmy
14 Nov 2024 13:06 UTC
17 points
0 comments9 min readLW link

SAEs are highly dataset de­pen­dent: a case study on the re­fusal direction

Connor Kissane, robertzk, Neel Nanda and Arthur Conmy
7 Nov 2024 5:22 UTC
65 points
4 comments14 min readLW link

Open Source Repli­ca­tion of An­thropic’s Cross­coder pa­per for model-diffing

Connor Kissane, robertzk, Arthur Conmy and Neel Nanda
27 Oct 2024 18:46 UTC
39 points
4 comments5 min readLW link

SAE fea­tures for re­fusal and syco­phancy steer­ing vectors

neverix, Dmitrii Kharlapenko, Arthur Conmy and Neel Nanda
12 Oct 2024 14:54 UTC
27 points
4 comments7 min readLW link

Base LLMs re­fuse too

Connor Kissane, robertzk, Arthur Conmy and Neel Nanda
29 Sep 2024 16:04 UTC
60 points
20 comments10 min readLW link

Ex­tract­ing SAE task fea­tures for in-con­text learning

Dmitrii Kharlapenko, neverix, Neel Nanda and Arthur Conmy
12 Aug 2024 20:34 UTC
31 points
1 comment9 min readLW link

Self-ex­plain­ing SAE features

Dmitrii Kharlapenko, neverix, Neel Nanda and Arthur Conmy
5 Aug 2024 22:20 UTC
60 points
13 comments10 min readLW link

JumpReLU SAEs + Early Ac­cess to Gemma 2 SAEs

Senthooran Rajamanoharan, Tom Lieberum, nps29, Arthur Conmy, Vikrant Varma, János Kramár and Neel Nanda
19 Jul 2024 16:10 UTC
48 points
10 comments1 min readLW link
(storage.googleapis.com)

SAEs (usu­ally) Trans­fer Between Base and Chat Models

Connor Kissane, robertzk, Arthur Conmy and Neel Nanda
18 Jul 2024 10:29 UTC
66 points
0 comments10 min readLW link

At­ten­tion Out­put SAEs Im­prove Cir­cuit Analysis

Connor Kissane, robertzk, Arthur Conmy and Neel Nanda
21 Jun 2024 12:56 UTC
33 points
3 comments19 min readLW link

Im­prov­ing Dic­tionary Learn­ing with Gated Sparse Autoencoders

Senthooran Rajamanoharan, Arthur Conmy, lewis smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah and Neel Nanda
25 Apr 2024 18:43 UTC
63 points
38 comments1 min readLW link
(arxiv.org)

[Full Post] Progress Up­date #1 from the GDM Mech In­terp Team

Neel Nanda, Arthur Conmy, lewis smith, Senthooran Rajamanoharan, Tom Lieberum, János Kramár and Vikrant Varma
19 Apr 2024 19:06 UTC
77 points
10 comments8 min readLW link

[Sum­mary] Progress Up­date #1 from the GDM Mech In­terp Team

Neel Nanda, Arthur Conmy, lewis smith, Senthooran Rajamanoharan, Tom Lieberum, János Kramár and Vikrant Varma
19 Apr 2024 19:06 UTC
72 points
0 comments3 min readLW link

We In­spected Every Head In GPT-2 Small us­ing SAEs So You Don’t Have To

robertzk, Connor Kissane, Arthur Conmy and Neel Nanda
6 Mar 2024 5:03 UTC
63 points
0 comments12 min readLW link

At­ten­tion SAEs Scale to GPT-2 Small

Connor Kissane, robertzk, Arthur Conmy and Neel Nanda
3 Feb 2024 6:50 UTC
78 points
4 comments8 min readLW link

Sparse Au­toen­coders Work on At­ten­tion Layer Outputs

Connor Kissane, robertzk, Arthur Conmy and Neel Nanda
16 Jan 2024 0:26 UTC
83 points
9 comments18 min readLW link

My best guess at the im­por­tant tricks for train­ing 1L SAEs

Arthur Conmy21 Dec 2023 1:59 UTC
37 points
4 comments3 min readLW link

[Paper] All’s Fair In Love And Love: Copy Sup­pres­sion in GPT-2 Small

CallumMcDougall, Arthur Conmy, Cody Rushing, Tom McGrath and Neel Nanda
13 Oct 2023 18:32 UTC
82 points
4 comments8 min readLW link

Three ways in­ter­pretabil­ity could be impactful

Arthur Conmy18 Sep 2023 1:02 UTC
47 points
8 comments4 min readLW link