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
6
1702
Prev
Next
MODEL
6
INDEX
Go
Explanations
The word good/great
Explanation Uploaded by User
No Scores
words "good" and "great" especially after the word "so"
Explanation Uploaded by User
No Scores
Positive adjectives such as "great", "good", and "all that"
Explanation Uploaded by User
No Scores
the words 'good', 'great' and 'for'
Explanation Uploaded by User
No Scores
Words meaning that something is good or nearby
Explanation Uploaded by User
No Scores
descriptors of positions, distance, or degree.
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/6/1702?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/1702?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
