Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
Home
Releases
Sparse Autoencoder for GPT2-Small - v5
Sparse Autoencoder for GPT2-Small - v5
OpenAI
ยท
github.com โ
gpt2sm-oai-2024
Jump To
Jump to Source/SAE
MODEL
0-att_128k-oai
Source/SAE
Go
Jump to Feature
MODEL
0-att_128k-oai
Source/SAE
INDEX
Go
Random Feature
Random
Search Explanations
All
By Release
By Model
By SAEs
Sparse Autoencoder for GPT2-Small - v5 2024
OpenAI
Show Dashboards
Hide Dashboards
Search via Inference
?
MODEL
Attention Out - 128k
All Layers
SEARCH
Run Example Search
Random
๐ฎ Food
๐ฐ News
๐ Literary
๐ฏ Personal
๐งโ๐ป Programming
๐งโ๐ฌ Technical
๐งโ๐ซ Academic
๐ผ Business
๐งโโ๏ธ Legal
๐งโ๐ซ Educational
๐ผ Cultural
Browse
MODEL
Attention Out - 128k
LAYER
Features in
GPT2-SM
@
0-att_128k-oai
Hover over a feature on the left to preview its details.
Click a feature to lock it and interact with it.
ยฉ Neuronpedia 2025
Privacy & Terms
Blog/RSS
GitHub
Slack
Twitter
Contact
