© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3156
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases or questions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Reviewed
    -0.67
     descript
    -0.65
    ◼
    -0.63
     rapp
    -0.63
     advisory
    -0.61
     ponds
    -0.61
     refin
    -0.60
     sworn
    -0.60
     repositories
    -0.60
     chanted
    -0.59
    POSITIVE LOGITS
     Prices
    0.71
     Flavoring
    0.71
     Hour
    0.66
     Ratings
    0.65
     Improved
    0.65
     Defenders
    0.64
     Ending
    0.64
    vana
    0.64
     Turning
    0.64
     Calm
    0.64
    Activations Density 0.032%

    No Known Activations