© 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. 3296
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a rationale or explanation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ��
    -0.76
    ��
    -0.75
    �
    -0.73
    �
    -0.71
     exting
    -0.68
    skin
    -0.65
    ENCY
    -0.65
    veyard
    -0.65
    pac
    -0.65
    �
    -0.63
    POSITIVE LOGITS
     follows
    1.02
     beh
    0.84
     surprises
    0.78
     begs
    0.76
     reson
    0.76
     underscores
    0.73
     counts
    0.73
     shines
    0.71
     baff
    0.70
     stands
    0.70
    Activations Density 0.091%

    No Known Activations