© 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. 3004
    Prev
    Next
    INDEX
    Explanations

    comparisons or similarities between concepts or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arrang
    -0.88
    natureconservancy
    -0.67
     imagination
    -0.64
    information
    -0.62
    ahime
    -0.61
    speech
    -0.60
     STATS
    -0.60
    senal
    -0.59
    Pokémon
    -0.58
    artifacts
    -0.57
    POSITIVE LOGITS
     awaited
    0.68
    endants
    0.64
    liest
    0.63
    uries
    0.61
    ailable
    0.61
    netflix
    0.60
    reb
    0.60
    rid
    0.59
     you
    0.59
    ocrats
    0.59
    Activations Density 0.087%

    No Known Activations