© 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. 2226
    Prev
    Next
    INDEX
    Explanations

    references to the speaker or personal experiences

    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
    ufact
    -0.80
    joice
    -0.79
    WARE
    -0.72
    quartered
    -0.66
     pestic
    -0.66
     priesthood
    -0.65
     srfAttach
    -0.63
     Tuls
    -0.62
    etheless
    -0.61
     Hobby
    -0.61
    POSITIVE LOGITS
    'd
    0.87
    'll
    0.81
    're
    0.80
     wanna
    0.77
     mean
    0.77
    bage
    0.76
     ['
    0.74
    'm
    0.73
    >(
    0.73
    've
    0.73
    Activations Density 0.324%

    No Known Activations