Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/RSS
GitHub
Slack
Twitter
Contact
Home
Releases
Transcoders Enable Fine-Grained Interpretable Circuit Analysis for Language Models
Transcoders Enable Fine-Grained Interpretable Circuit Analysis for Language Models
Jacob Dunefsky · Philippe Chlenski
·
lesswrong.com ↗
gpt2sm-tres-dc
Jump To
Jump to Source/SAE
MODEL
0-tres-dc
Source/SAE
Go
Jump to Feature
MODEL
0-tres-dc
Source/SAE
INDEX
Go
Random Feature
Random
Search Explanations
All
By Release
By Model
By SAEs
Transcoders Enable Fine-Grained Interpretable Circuit Analysis
Jacob Dunefsky · Philippe Chlenski
Show Dashboards
Hide Dashboards
Search via Inference
?
Inference is not currently not enabled for this.
Contact the Neuronpedia team to request it.
Browse
MODEL
Transcoders Residuals
LAYER
Features in
GPT2-SM
@
0-tres-dc
Hover over a feature on the left to preview its details.
Click a feature to lock it and interact with it.