© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1252
    Prev
    Next
    INDEX
    Explanations

    parentheses in the text

    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
     Investig
    -0.77
     flawed
    -0.74
     populated
    -0.74
     loaded
    -0.73
     compr
    -0.73
     tough
    -0.73
     slightly
    -0.73
     clashes
    -0.73
     heavily
    -0.73
     busy
    -0.72
    POSITIVE LOGITS
    including
    1.34
    e
    1.23
    say
    1.20
    especially
    1.18
    minus
    1.18
    outside
    1.17
    except
    1.16
    like
    1.16
    example
    1.15
    such
    1.15
    Activations Density 0.084%

    No Known Activations