© 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. 2401
    Prev
    Next
    INDEX
    Explanations

    references to "back" in various contexts

    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
    adian
    -0.72
    unts
    -0.70
     Median
    -0.70
     Mehran
    -0.68
    owicz
    -0.67
    ikk
    -0.67
    kel
    -0.66
    @@@@
    -0.66
    ison
    -0.66
    ��
    -0.66
    POSITIVE LOGITS
    breaking
    0.99
    woods
    0.87
    channel
    0.86
    bones
    0.82
    doors
    0.79
    office
    0.77
    stab
    0.77
    chat
    0.77
    fired
    0.77
    drops
    0.76
    Activations Density 0.041%

    No Known Activations