© 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. 2041
    Prev
    Next
    INDEX
    Explanations

    key nouns and verbs related to significant actions and roles

    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
    =-=-=-=-
    -0.42
    igslist
    -0.42
    ccording
    -0.41
     lapt
    -0.41
    BILITIES
    -0.40
    Reviewer
    -0.39
     pestic
    -0.39
    emetery
    -0.39
    OPLE
    -0.38
    ruciating
    -0.38
    POSITIVE LOGITS
    horn
    0.40
    ipp
    0.38
    nard
    0.37
    iva
    0.37
    gar
    0.37
    oran
    0.37
    irgin
    0.36
    young
    0.35
    oak
    0.35
    gate
    0.35
    Activations Density 1.534%

    No Known Activations