Sign up to save your podcasts
Or
Share “[Paper] A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders” by chanind, TomasD, hrdkbhatnagar, Joseph Bloom
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“[Paper] A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders” by chanind, TomasD, hrdkbhatnagar, Joseph Bloom
This research was completed for London AI Safety Research (LASR) Labs 2024. The team was supervised by Joseph Bloom (Decode Research). Find out more about the programme and express interest in upcoming iterations here.
This high level summary will be most accessible to those with relevant context including an understanding of SAEs. The importance of this work rests in part on the surrounding hype, and potential philosophical issues. We encourage readers seeking technical details to read the paper on arxiv.
TLDR: This is a short post summarising the key ideas and implications of our recent work studying how character information represented in language models is extracted by SAEs. Our most important result shows that SAE latents can appear to classify some feature of the input, but actually turn out to be quite unreliable classifiers (much worse than linear probes). We think this unreliability is in part due to difference [...]
The original text contained 1 footnote which was omitted from this narration.
The original text contained 1 image which was described by AI.
---
First published:
September 25th, 2024
Source:
https://www.lesswrong.com/posts/3zBsxeZzd3cvuueMJ/paper-a-is-for-absorption-studying-feature-splitting-and
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
View all episodes
By LessWrongThis research was completed for London AI Safety Research (LASR) Labs 2024. The team was supervised by Joseph Bloom (Decode Research). Find out more about the programme and express interest in upcoming iterations here.
This high level summary will be most accessible to those with relevant context including an understanding of SAEs. The importance of this work rests in part on the surrounding hype, and potential philosophical issues. We encourage readers seeking technical details to read the paper on arxiv.
TLDR: This is a short post summarising the key ideas and implications of our recent work studying how character information represented in language models is extracted by SAEs. Our most important result shows that SAE latents can appear to classify some feature of the input, but actually turn out to be quite unreliable classifiers (much worse than linear probes). We think this unreliability is in part due to difference [...]
The original text contained 1 footnote which was omitted from this narration.
The original text contained 1 image which was described by AI.
---
First published:
September 25th, 2024
Source:
https://www.lesswrong.com/posts/3zBsxeZzd3cvuueMJ/paper-a-is-for-absorption-studying-feature-splitting-and
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
More shows like LessWrong (30+ Karma)
View all
Making Sense with Sam Harris
26,382 Listeners
Conversations with Tyler
2,386 Listeners
The Peter Attia Drive
7,925 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,134 Listeners
ManifoldOne
87 Listeners
Your Undivided Attention
1,456 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
9,048 Listeners
Machine Learning Street Talk (MLST)
87 Listeners
Dwarkesh Podcast
387 Listeners
Hard Fork
5,426 Listeners
The Ezra Klein Show
15,207 Listeners
Moonshots with Peter Diamandis
472 Listeners
No Priors: Artificial Intelligence | Technology | Startups
120 Listeners
Latent Space: The AI Engineer Podcast
75 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
456 Listeners