Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
GPT2-Small
11
840
Prev
Next
MODEL
11
INDEX
Go
Explanations
tokens: " An", " Ag", " She", " We", " Sw"; phrases using "densest known"; " Consent"
Explanation Uploaded by User
No Scores
Tokens "An" "Ag" "She", "We", "Sw" especially starting last names typically Indian in origin; "densest known"
Explanation Uploaded by User
No Scores
First token in a last name, especially "An" in "Anand"
Explanation Uploaded by User
No Scores
word fragments, often related to demographics and regions.
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/11/840?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/11/840?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
