© 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
GPT2-SMALL · MLP Neurons - Layer 6 · 644 ｜ Neuronpedia
Home
GPT2-Small
MLP Neurons - Layer 6
644
Prev
Next
MODEL
Neurons Layer 6
Layer 5
Layer 7
INDEX
Go
Explanations
Contractions ending with “‘d be”
Explanation Uploaded by User
No Scores
phrases indicated hypotheticals (eg "wouldn't be", "it'd be", "I'd be", etc)
Explanation Uploaded by User
No Scores
Would or would not be
Explanation Uploaded by User
No Scores
the contraction ‘d or the phrase “wouldn’t be”
Explanation Uploaded by User
No Scores
contractions with "be" following
Explanation Uploaded by User
No Scores
contractions with the base verb "would."
oai_token-act-pair · gpt-4-turbo
No Scores
Statements about hypotheticals or counterfactuals
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/6/644?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/6/644?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
