Neel Nanda

Karma: 6,983

Mechanistic Interpretability Workshop Happening at ICML 2024!

Neel Nanda, LawrenceC and Fazl

3 May 2024 1:18 UTC

48 points

6 comments1 min readLW link

Transcoders enable fine-grained interpretable circuit analysis for language models

Jacob Dunefsky, Philippe Chlenski and Neel Nanda

30 Apr 2024 17:58 UTC

59 points

12 comments17 min readLW link

Refusal in LLMs is mediated by a single direction

Andy Arditi, Oscar Obeso, Aaquib111, wesg and Neel Nanda

27 Apr 2024 11:13 UTC

187 points

79 comments10 min readLW link

Improving Dictionary Learning with Gated Sparse Autoencoders

Senthooran Rajamanoharan, Arthur Conmy, lsgos, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah and Neel Nanda

25 Apr 2024 18:43 UTC

62 points

35 comments1 min readLW link

(arxiv.org)

How to use and interpret activation patching

StefanHex and Neel Nanda

24 Apr 2024 8:35 UTC

12 points

0 comments18 min readLW link

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

Neel Nanda, Arthur Conmy, lsgos, Senthooran Rajamanoharan, Tom Lieberum, János Kramár and Vikrant Varma

19 Apr 2024 19:06 UTC

71 points

8 comments8 min readLW link

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

Neel Nanda, Arthur Conmy, lsgos, Senthooran Rajamanoharan, Tom Lieberum, János Kramár and Vikrant Varma

19 Apr 2024 19:06 UTC

68 points

0 comments3 min readLW link

AtP*: An efficient and scalable method for localizing LLM behaviour to components

Neel Nanda, János Kramár, Tom Lieberum and Rohin Shah

18 Mar 2024 17:28 UTC

19 points

0 comments1 min readLW link

(arxiv.org)

Laying the Foundations for Vision and Multimodal Mechanistic Interpretability & Open Problems

Sonia Joseph and Neel Nanda

13 Mar 2024 17:09 UTC

41 points

13 comments14 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

56 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

76 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

82 points

5 comments19 min readLW link

Case Studies in Reverse-Engineering Sparse Autoencoder Features by Using MLP Linearization

Jacob Dunefsky, Philippe Chlenski, Senthooran Rajamanoharan and Neel Nanda

14 Jan 2024 2:06 UTC

23 points

0 comments42 min readLW link

Fact Finding: Do Early Layers Specialise in Local Processing? (Post 5)

Neel Nanda, Senthooran Rajamanoharan, János Kramár and Rohin Shah

23 Dec 2023 2:46 UTC

18 points

0 comments4 min readLW link

Fact Finding: How to Think About Interpreting Memorisation (Post 4)

Senthooran Rajamanoharan, Neel Nanda, János Kramár and Rohin Shah

23 Dec 2023 2:46 UTC

22 points

0 comments9 min readLW link

Fact Finding: Trying to Mechanistically Understanding Early MLPs (Post 3)

Neel Nanda, Senthooran Rajamanoharan, János Kramár and Rohin Shah

23 Dec 2023 2:46 UTC

9 points

0 comments16 min readLW link

Fact Finding: Simplifying the Circuit (Post 2)

Senthooran Rajamanoharan, Neel Nanda, János Kramár and Rohin Shah

23 Dec 2023 2:45 UTC

18 points

3 comments14 min readLW link

Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level (Post 1)

Neel Nanda, Senthooran Rajamanoharan, János Kramár and Rohin Shah

23 Dec 2023 2:44 UTC

106 points

6 comments22 min readLW link

How useful is mechanistic interpretability?

ryan_greenblatt, Neel Nanda, Buck and habryka

1 Dec 2023 2:54 UTC

156 points

53 comments25 min readLW link

Open Source Replication & Commentary on Anthropic’s Dictionary Learning Paper

Neel Nanda23 Oct 2023 22:38 UTC

91 points

12 comments9 min readLW link