© 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. 3155
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "impact."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    akia
    -0.77
    asks
    -0.76
    eworld
    -0.72
    akra
    -0.69
     suspic
    -0.66
    ombies
    -0.65
    allery
    -0.64
    Reviewer
    -0.64
    arah
    -0.63
     hotter
    -0.63
    POSITIVE LOGITS
    olate
    0.67
     Clause
    0.64
    ful
    0.64
    riber
    0.63
    quist
    0.63
     Tackle
    0.59
     Demon
    0.58
     booster
    0.58
    INGTON
    0.57
    span
    0.57
    Activations Density 0.082%

    No Known Activations