© 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. 3332
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial or mechanical processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     separat
    -0.80
     smugg
    -0.77
     compet
    -0.77
     eas
    -0.75
     whereabouts
    -0.74
     visitation
    -0.74
     surn
    -0.74
     smuggling
    -0.73
     trespass
    -0.72
     infring
    -0.72
    POSITIVE LOGITS
    oric
    0.93
    enders
    0.86
    ends
    0.85
    udos
    0.85
    arks
    0.81
    endant
    0.81
    ptive
    0.80
    ension
    0.80
    ENTION
    0.79
    END
    0.79
    Activations Density 0.131%

    No Known Activations