Record · corpus.blog/posts/01a08219-ddaf-7384-bcb4-f2bfaeb0d08e

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Transformer Circuits · published 4 October 2023

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at transformer-circuits.pub Wayback capture

13blogs citing

First cited: 3 Nov 2023
Most recent: 14 Jul 2026
Rank this month: not ranked
Links from this post: 10
Words captured: 4,831

Cited by

Blog

In the post

Date

tylercrosse.com

Notes on Towards Monosemanticity and Scaling Monosemanticity Read at the source ↗

14 Jul 2026

tylercrosse.com

Transformer Circuits Thread Notes Read at the source ↗

12 Jul 2026

ludwigabap.bearblog.dev

Saturday Paper Reading Read at the source ↗

26 Apr 2025

shreyansjainn.github.io

Feature Geometry in Toy Models - Pentagon vs Hexagon Read at the source ↗

28 Jan 2025

aiimpacts.org

Towards the Operationalization of Philosophy & Wisdom Read at the source ↗

27 Oct 2024

bionicteaching.com

Weekly Web Harvest for 2024-09-29 Read at the source ↗

6 Oct 2024

cyberchris.xyz

Dead Man's Switch: Combining SAE Features and Refusal Intervention in LLMs Read at the source ↗

18 Sept 2024

cgad.ski

When Numbers Are Bits: How Efficient Are Distributed Representations? Read at the source ↗

17 Aug 2024

Ben Kuhn

Categories of leadership on technical teams Read at the source ↗

21 Jul 2024

adamjones.me

AI as a corporation (or, an intro to AI safety?) Read at the source ↗

14 Jul 2024

kipply

Things Read | Nov/Dec 2023 Read at the source ↗

2 Jan 2024

blog.vero.site

Despite Everything Read at the source ↗

1 Jan 2024

corinwagen.github.io

Bitter Lessons in Chemistry Read at the source ↗

1 Dec 2023

kolaayonrinde.com

Dictionary Learning with Sparse AutoEncoders Read at the source ↗

3 Nov 2023

Links from this post

Link

Host

https://transformer-circuits.pub/2023/monosemantic-features/vis/a-neurons.html?ordering=index

transformer-circuits.pub

Toy Models of Superposition Read at the source ↗

transformer-circuits.pub

Distributed Representations: Composition & Superposition Read at the source ↗

transformer-circuits.pub

https://transformer-circuits.pub/2023/monosemantic-features/vis/

transformer-circuits.pub

https://transformer-circuits.pub/2023/monosemantic-features/vis/a1.html

transformer-circuits.pub

https://transformer-circuits.pub/2023/monosemantic-features/vis/index.html

transformer-circuits.pub

Circuits Updates — July 2023 Read at the source ↗

transformer-circuits.pub

https://en.wikipedia.org/wiki/Sparse_dictionary_learning

en.wikipedia.org

https://en.wikipedia.org/wiki/Compressed_sensing

en.wikipedia.org

Circuits Updates — May 2023 Read at the source ↗

transformer-circuits.pub