© 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. 3224
    Prev
    Next
    INDEX
    Explanations

    sentences or statements that provide information or conclusions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     nostalg
    -0.65
     tremend
    -0.65
    */(
    -0.64
    OK
    -0.64
    umbn
    -0.63
     desper
    -0.61
     priceless
    -0.61
     liking
    -0.61
    umbnails
    -0.61
     boulder
    -0.59
    POSITIVE LOGITS
     Developers
    0.76
     Sources
    0.72
     Ratings
    0.71
     Users
    0.71
     Regulatory
    0.70
     Sul
    0.64
     EPA
    0.64
     Yards
    0.63
     Opp
    0.63
     Ellison
    0.63
    Activations Density 0.357%

    No Known Activations