© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 10243
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to people named Karen

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Karen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheus
    -0.81
    udic
    -0.73
    othal
    -0.70
    cision
    -0.70
    rid
    -0.69
    aneous
    -0.68
     derogatory
    -0.67
     Logged
    -0.66
    igated
    -0.66
    NSA
    -0.65
    POSITIVE LOGITS
     Karen
    1.19
     Sue
    0.93
     lapt
    0.80
    ratom
    0.77
     Borders
    0.75
     Kuro
    0.75
     Silk
    0.70
    itably
    0.70
    ites
    0.69
    taining
    0.69
    Activations Density 0.007%

    No Known Activations