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
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
pyvene.ai, The Stanford NLP Group
·
github.com ↗
axbench
Jump To
Jump to Source/SAE
MODEL
20-axbench-reft-r1-res-16k
Source/SAE
Go
Jump to Feature
MODEL
20-axbench-reft-r1-res-16k
Source/SAE
INDEX
Go
Random Feature
Random
Search Explanations
All
By Release
By Model
By SAEs
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
pyvene.ai, The Stanford NLP Group
Show Dashboards
Hide Dashboards
Browse
MODEL
LAYER
Features in
GEMMA-2-9B-IT
@
20-axbench-reft-r1-res-16k
Hover over a feature on the left to preview its details.
Click a feature to lock it and interact with it.
