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
70
Prev
Next
MODEL
6
INDEX
Go
Explanations
the token 'he' after 'th' ot '[t]'
No Scores
he
No Scores
Letters He from the word the
No Scores
the token "he" as part of the word "the", the phrase " of the", " Al-"
No Scores
Definite articles, especially "the", and especially when "the" is preceded by brackets (such as [T]he), or there is a typo in "the".
No Scores
Typo of the word "the"
No Scores
"he" as a syllable after a square letter or word "H"
No Scores
prepositions and possessive pronouns.
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/6/70?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/70?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