© 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. 18720
    Prev
    Next
    INDEX
    Explanations

    items of clothing or costumes, particularly outfits mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "outfit" or related terms

    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
    birth
    -0.79
    ollow
    -0.73
    ouston
    -0.65
    common
    -0.63
    ollo
    -0.63
    interrupted
    -0.62
     Pell
    -0.61
     Quincy
    -0.61
     Lakes
    -0.61
    negative
    -0.61
    POSITIVE LOGITS
     outfit
    1.27
     outfits
    1.19
     apparel
    0.90
     garments
    0.89
     attire
    0.87
     coats
    0.84
     wardrobe
    0.83
     jeans
    0.81
    puter
    0.81
    aton
    0.79
    Activations Density 0.008%

    No Known Activations