Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Activation Engineering/Neuron SAE/Selective SAE/
Top-K SAE
Search

Top-K SAE

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2024 Nov 18 20:25
Editor
Editor
Seonglae ChoSeonglae Cho
Edited
Edited
2025 Jun 16 22:3
Refs
Refs

2024,
Leo Gao
et al.

Limit each input token to have a maximum of k feature activations
Problem: Some tokens can be easily reconstructed, but others need more features
OpenAI Top-k SAE
 
 
 
cdn.openai.com
https://cdn.openai.com/papers/sparse-autoencoders.pdf
Feature Browser
SAE viewer
Web site created using create-react-app
SAE viewer
https://openaipublic.blob.core.windows.net/sparse-autoencoder/sae-viewer/index.html
 
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Activation Engineering/Neuron SAE/Selective SAE/
Top-K SAE
Copyright Seonglae Cho