Logan Riggs

Karma: 2,291

Was Releasing Claude-3 Net-Negative?

Logan Riggs27 Mar 2024 17:41 UTC

42 points

5 comments4 min readLW link

Improving SAE’s by Sqrt()-ing L1 & Removing Lowest Activating Features

Logan Riggs and Jannik Brinkmann

15 Mar 2024 16:30 UTC

17 points

5 comments4 min readLW link

Finding Sparse Linear Connections between Features in LLMs

Logan Riggs, Sam Mitchell and Eccentricity

9 Dec 2023 2:27 UTC

68 points

5 comments10 min readLW link

Sparse Autoencoders: Future Work

Logan Riggs and Aidan Ewart

21 Sep 2023 15:30 UTC

34 points

5 comments6 min readLW link

Sparse Autoencoders Find Highly Interpretable Directions in Language Models

Logan Riggs, Hoagy, Aidan Ewart and Robert_AIZI

21 Sep 2023 15:30 UTC

156 points

7 comments5 min readLW link

Really Strong Features Found in Residual Stream

Logan Riggs8 Jul 2023 19:40 UTC

69 points

6 comments2 min readLW link

(tentatively) Found 600+ Monosemantic Features in a Small LM Using Sparse Autoencoders

Logan Riggs5 Jul 2023 16:49 UTC

58 points

1 comment7 min readLW link

[Replication] Conjecture’s Sparse Coding in Small Transformers

Hoagy and Logan Riggs

16 Jun 2023 18:02 UTC

52 points

0 comments5 min readLW link

[Replication] Conjecture’s Sparse Coding in Toy Models

Hoagy and Logan Riggs

2 Jun 2023 17:34 UTC

23 points

0 comments1 min readLW link

[Simulators seminar sequence] #2 Semiotic physics—revamped

Jan, Charlie Steiner, Logan Riggs, janus, jacquesthibs, metasemi, Michael Oesterle, Lucas Teixeira, peligrietzer and remember

27 Feb 2023 0:25 UTC

23 points

23 comments13 min readLW link

Making Implied Standards Explicit

Logan Riggs25 Feb 2023 20:02 UTC

20 points

0 comments4 min readLW link

Proposal for Inducing Steganography in LMs

Logan Riggs12 Jan 2023 22:15 UTC

22 points

2 comments2 min readLW link

[Simulators seminar sequence] #1 Background & shared assumptions

Jan, Charlie Steiner, Logan Riggs, janus, jacquesthibs, metasemi, Michael Oesterle, Lucas Teixeira, peligrietzer and remember

2 Jan 2023 23:48 UTC

49 points

4 comments3 min readLW link

Results from a survey on tool use and workflows in alignment research

jacquesthibs, Jan, janus and Logan Riggs

19 Dec 2022 15:19 UTC

79 points

2 comments19 min readLW link

A descriptive, not prescriptive, overview of current AI Alignment Research

Jan, Logan Riggs, jacquesthibs and janus

6 Jun 2022 21:59 UTC

138 points

21 comments7 min readLW link

Frame for Take-Off Speeds to inform compute governance & scaling alignment

Logan Riggs13 May 2022 22:23 UTC

15 points

2 comments2 min readLW link

Alignment as Constraints

Logan Riggs13 May 2022 22:07 UTC

10 points

0 comments2 min readLW link

Make a Movie Showing Alignment Failures

Logan Riggs13 Apr 2022 21:54 UTC

75 points

11 comments2 min readLW link

Convincing People of Alignment with Street Epistemology

Logan Riggs12 Apr 2022 23:43 UTC

54 points

4 comments3 min readLW link

Roam Research Mobile is Out!

Logan Riggs8 Apr 2022 19:05 UTC

12 points

0 comments1 min readLW link