corpus.blog
41,715 blogs · 5,239,565 posts Claim your blog
Record · corpus.blog/posts/01a0871f-8d91-7028-b7f1-21c202cafb8e

An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability

adamkarvonen.github.io · published 11 June 2024

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 adamkarvonen.github.io Wayback capture
1blogs citing
First cited
30 Jan 2025
Most recent
30 Jan 2025
Rank this month
not ranked
External links
23
Words captured
2,881

Cited by

Blog
In the post
Date
bneo.xyz
angpao and autoencoders Read at the source ↗
30 Jan 2025

Links from this post

Link
Host
https://www.sciencedirect.com/science/article/pii/S0042698997001697
sciencedirect.com
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet Read at the source ↗
transformer-circuits.pub
https://transformer-circuits.pub/2023/monosemantic-features
transformer-circuits.pub
https://www.lesswrong.com/posts/LnHowHgmrMbWtpkxx/intro-to-superposition-and-sparse-autoencoders-colab
lesswrong.com
https://transformer-circuits.pub/2022/toy_model/
transformer-circuits.pub
https://en.wikipedia.org/wiki/Autoencoder
en.wikipedia.org
https://arxiv.org/abs/2005.14165
arxiv.org
https://medium.com/@NoamShazeer/shape-suffixes-good-coding-style-f836e72e24fd
medium.com
https://github.com/openai/sparse_autoencoder/blob/main/sparse_autoencoder/model.py
github.com
https://github.com/jbloomAus/SAELens/blob/main/sae_lens/sae.py
github.com
https://github.com/saprmarks/dictionary_learning/blob/main/dictionary.py
github.com
https://www.alignmentforum.org/posts/Nkx6yWZNbAsfvic98/batchtopk-a-simple-improvement-for-topk-saes
alignmentforum.org
https://github.com/saprmarks/dictionary_learning/blob/main/trainers/batch_top_k.py
github.com
https://cdn.openai.com/papers/sparse-autoencoders.pdf
cdn.openai.com
https://arxiv.org/abs/2407.14435
arxiv.org
https://www.alignmentforum.org/posts/fKuugaxt2XLTkASkk/open-source-replication-and-commentary-on-anthropic-s
alignmentforum.org
https://transformer-circuits.pub/2024/scaling-monosemanticity/
transformer-circuits.pub
https://x.com/saprmarks/status/1758253577888493901
x.com
Golden Gate Claude Read at the source ↗
anthropic.com
https://arxiv.org/abs/2404.16014
arxiv.org
https://arxiv.org/abs/2403.19647
arxiv.org
https://www.dwarkeshpatel.com/p/dario-amodei
dwarkeshpatel.com
https://arxiv.org/abs/2405.12241
arxiv.org
Elsewhere on adamkarvonen.github.io (1)