© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1127
    Prev
    Next
    INDEX
    Explanations

    phrases centered around the concept of doing something for a specific purpose or justification

    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
    ���
    -0.67
    Filename
    -0.59
    cludes
    -0.56
     inconven
    -0.55
    eters
    -0.54
     Hou
    -0.53
    elta
    -0.52
     perm
    -0.52
     Johannes
    -0.51
     exceptions
    -0.51
    POSITIVE LOGITS
     of
    0.94
    of
    0.89
    liest
    0.76
     Of
    0.71
    wards
    0.69
     OF
    0.69
    Of
    0.68
    wife
    0.67
    ally
    0.65
    ward
    0.62
    Activations Density 0.044%

    No Known Activations