© 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. 2085
    Prev
    Next
    INDEX
    Explanations

    instances of the word "asked."

    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
     dotted
    -0.72
    ordered
    -0.67
    atten
    -0.66
     unders
    -0.63
    OUND
    -0.61
    reen
    -0.61
    lined
    -0.60
    osph
    -0.60
     witness
    -0.59
    ONT
    -0.59
    POSITIVE LOGITS
    agall
    0.72
     sorts
    0.69
    Tea
    0.68
     particulars
    0.68
    about
    0.67
    ican
    0.66
    elf
    0.65
     secession
    0.65
     explan
    0.64
    asse
    0.61
    Activations Density 0.012%

    No Known Activations