© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    references to presentations and their details

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    brother
    -0.74
    wings
    -0.71
    chin
    -0.70
    tiny
    -0.69
    iens
    -0.67
    authorized
    -0.67
    cens
    -0.66
    worst
    -0.63
    twitter
    -0.63
    urs
    -0.62
    POSITIVE LOGITS
     ›
    0.64
    iculture
    0.63
    ":["
    0.63
    PLIED
    0.63
     Discuss
    0.62
     immersed
    0.60
     Gadget
    0.59
     Greenberg
    0.58
     Quant
    0.58
     maj
    0.58
    Activations Density 2.301%

    No Known Activations