© 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. 2872
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a critical or pivotal moment

    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
    omething
    -0.93
    verified
    -0.73
     vou
    -0.70
    comed
    -0.70
    fters
    -0.70
    ovych
    -0.68
    yang
    -0.66
    OTS
    -0.63
    Ped
    -0.62
    enegger
    -0.61
    POSITIVE LOGITS
     pains
    0.92
     fault
    0.87
    eness
    0.86
     disadvantage
    0.80
     liberty
    0.74
    CVE
    0.74
     variance
    0.70
     ease
    0.68
     stake
    0.66
    ision
    0.65
    Activations Density 0.049%

    No Known Activations