© 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. 2227
    Prev
    Next
    INDEX
    Explanations

    specific types of items or products

    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
    bryce
    -0.75
    vernment
    -0.72
    NetMessage
    -0.66
    redients
    -0.66
     hots
    -0.63
    Downloadha
    -0.59
    hots
    -0.59
     mosqu
    -0.59
    %%%%
    -0.58
     rall
    -0.58
    POSITIVE LOGITS
     cannibal
    0.70
    bart
    0.58
    $.
    0.57
     Prosecut
    0.55
     weigh
    0.55
     coughing
    0.54
    mart
    0.52
    inho
    0.52
    anski
    0.52
    sch
    0.51
    Activations Density 0.390%

    No Known Activations