Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog/Podcast
NEW
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
GPT2-Small
6
2796
Prev
Next
MODEL
6
INDEX
Go
Explanations
athletes getting red cards, someone losing their job or resigning, or Donald Trump's Muslim travel ban
No Scores
negative impact, like getting a red card or banning from things
No Scores
phrases indicating restrictive actions or rules.
oai_token-act-pair · gpt-4-turbo
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/6/2796?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/2796?embed=true&embedexplanation=true&embedplots=true&embedtest=true
•
phrases and idioms
Add to List
▼
No Comments
ADD
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
