41,554 blogs · 4,969,865 posts Claim your blog

Record · corpus.blog/posts/01a08219-ddaf-7384-bcb4-f2bfb405db33

Mechanistic Interpretability, Variables, and the Importance of Interpretable Bases

Transformer Circuits · published 27 June 2022

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

2blogs citing

First cited: 8 Dec 2022
Most recent: 4 May 2023
Rank this month: not ranked
External links: 5
Words captured: 2,139

Cited by

Blog

In the post

Date

Factorize your language models Read at the source ↗

4 May 2023

How we could stumble into AI catastrophe Read at the source ↗

13 Jan 2023

High-level hopes for AI alignment Read at the source ↗

15 Dec 2022

AI Safety Seems Hard to Measure Read at the source ↗

8 Dec 2022

Links from this post

Link

Host

https://colah.github.io/posts/2014-03-NN-Manifolds-Topology/

colah.github.io

Visualizing Weights Read at the source ↗

Thread: Circuits Read at the source ↗

https://math.berkeley.edu/~kpmann/Lakatos.pdf

math.berkeley.edu

Branch Specialization Read at the source ↗

Elsewhere on transformer-circuits.pub (3)

A Mathematical Framework for Transformer Circuits Read at the source ↗

transformer-circuits.pub

Softmax Linear Units Read at the source ↗

transformer-circuits.pub

https://transformer-circuits.pub/

transformer-circuits.pub