© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    references to specific moments or stages in a process

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     perk
    -0.72
    SPONSORED
    -0.70
    galitarian
    -0.69
    \\\\\\\\
    -0.68
    xtap
    -0.68
    jamin
    -0.68
    zbek
    -0.66
    pload
    -0.65
    TextColor
    -0.63
    Redd
    -0.63
    POSITIVE LOGITS
    atoon
    0.66
     along
    0.66
     warrants
    0.65
     ACTIONS
    0.64
    outer
    0.64
    onto
    0.62
    ngth
    0.62
     during
    0.61
     hairs
    0.58
     activ
    0.58
    Activations Density 0.047%

    No Known Activations