© 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. 518
    Prev
    Next
    INDEX
    Explanations

    quoted phrases or citations 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
     RFC
    -0.87
     pg
    -0.84
     compartment
    -0.80
     cm
    -0.73
     MT
    -0.71
     checkpoint
    -0.71
     Gustav
    -0.70
     moot
    -0.69
     mm
    -0.68
     rack
    -0.68
    POSITIVE LOGITS
    duty
    1.14
    matter
    1.12
    Definition
    1.09
    sweet
    1.09
    Agent
    1.06
    dark
    1.04
    shine
    1.02
    rules
    1.02
    good
    1.01
    Ru
    1.01
    Activations Density 0.045%

    No Known Activations