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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12093
    Prev
    Next
    INDEX
    Explanations

    fashion-related terms and clothing descriptions, particularly focusing on fabric and garment details

    oai_token-act-pair · gpt-3.5-turbo

    elements and descriptions related to clothing and fashion choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertodd
    -0.77
     demol
    -0.74
    Poké
    -0.72
    uclear
    -0.72
    AMD
    -0.71
     Buildings
    -0.70
    acio
    -0.69
    minent
    -0.69
    Activity
    -0.68
    adeon
    -0.68
    POSITIVE LOGITS
     jeans
    1.43
     trousers
    1.36
     waist
    1.35
     denim
    1.33
     sleeves
    1.28
     sweater
    1.28
     straps
    1.27
     zipper
    1.25
     garment
    1.24
     shirt
    1.23
    Activations Density 0.197%

    No Known Activations