Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
GPT2-Small
6
2523
Prev
Next
MODEL
6
INDEX
Go
Explanations
“inst” in uninstalling
Explanation Uploaded by User
No Scores
uninstalling, #uninstallsnapchat or #boycottsnapchat, javma, OAUTH_TOKEN_REVOKED
Explanation Uploaded by User
No Scores
words containing the letter 'h' or 'f' with slightly stronger activation for 'h'.
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/6/2523?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/2523?embed=true&embedexplanation=true&embedplots=true&embedtest=true
•
words
•
source code or software logs
detects OAUTH_TOKEN_REVOKED and similar
•
polysemantic or mysterious neurons
•
software or computing discussion
Add to List
▼
No Comments
ADD
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
