© 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. 2553
    Prev
    Next
    INDEX
    Explanations

    instances of the HTML 'a' tag used for hyperlinks

    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
    ruby
    -0.73
    ROR
    -0.68
    FI
    -0.66
    risome
    -0.65
    FTWARE
    -0.62
    jriwal
    -0.60
    ACP
    -0.59
    rica
    -0.59
    uncture
    -0.59
    ody
    -0.59
    POSITIVE LOGITS
    toe
    0.69
    romy
    0.63
    itiz
    0.62
     href
    0.60
    ijah
    0.58
     civ
    0.57
    oft
    0.56
     emot
    0.56
     spotting
    0.56
     derive
    0.55
    Activations Density 0.011%

    No Known Activations