© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
MAY 26
Assistant Axis
JAN 26
Circuit Tracer
APR 26
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
Docs
Community
Blog
Privacy & Terms
Contact
Sign In
Home
GPT2-Small
MLP Neurons - Layer 6
679
Prev
Next
MODEL
Neurons Layer 6
Layer 5
Layer 7
INDEX
Go
Explanations
numbers written in english, measurements such as "two" "three" "hundred" "dozen"
Explanation Uploaded by User
No Scores
words and phrases implying plurality
Explanation Uploaded by User
No Scores
" of" and amounts shortly after " of"
Explanation Uploaded by User
No Scores
amounts (names of numbers, "many", "few", etc...) and the associated "of" and object
Explanation Uploaded by User
No Scores
numbers in news articles
Explanation Uploaded by User
No Scores
descriptive or quantitative articles
Explanation Uploaded by User
No Scores
quantities and numerical associations.
oai_token-act-pair · gpt-4-turbo
No Scores
Amounts written with letters, in the context of politics, geographic, history and similar
Explanation Uploaded by User
No Scores
Amounts
Explanation Uploaded by User
No Scores
New Auto-Interp
AutoInterp Type
claude-haiku-5-5
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gpt2-small/6/679?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/679?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
