© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3032
    Prev
    Next
    INDEX
    Explanations

    instances of people responding or reacting to reports or statements

    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
    SCP
    -0.84
    channelAvailability
    -0.73
    IDs
    -0.68
    bably
    -0.67
    BG
    -0.66
    mine
    -0.65
    Population
    -0.64
    package
    -0.64
    vision
    -0.63
    BIP
    -0.62
    POSITIVE LOGITS
    ascus
    0.67
     echoes
    0.67
    ILA
    0.65
     supporters
    0.63
    laden
    0.62
    agher
    0.62
     commentary
    0.62
    iban
    0.59
     mirrored
    0.59
     Reply
    0.58
    Activations Density 0.240%

    No Known Activations