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
1272
Prev
Next
MODEL
6
INDEX
Go
Explanations
proper names, as well as personal pronouns "him", "her", "me".
No Scores
possessive pronouns followed by nouns, with a focus on personal situations.
oai_token-act-pair · gpt-4-turbo
No Scores
"French"; parts of words, such as "z", "Patrick", "e", "L" in "NoDAPL", "ark"; pronouns and surrounding verbs or adjectives
No Scores
Names
No Scores
various letters of the final part of proper nouns
No Scores
last letter of a word
No Scores
the last token of unusual proper nouns, 2nd and 3rd person pronouns
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/6/1272?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/1272?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations