© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1531
    Prev
    Next
    INDEX
    Explanations

    profile-related information and user statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cooldown
    -0.67
     helic
    -0.66
    audi
    -0.62
     heaviest
    -0.60
     externally
    -0.60
     Corm
    -0.59
     Sind
    -0.57
     Nadu
    -0.57
     whis
    -0.56
    Prev
    -0.55
    POSITIVE LOGITS
     Aug
    0.65
    DragonMagazine
    0.64
    istries
    0.64
     Mysteries
    0.62
    azo
    0.60
    asty
    0.60
     July
    0.59
     August
    0.59
    live
    0.59
     September
    0.58
    Activations Density 1.669%

    No Known Activations