© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7815
    Prev
    Next
    INDEX
    Explanations

    words related to or associated with clothing

    oai_token-act-pair · gpt-3.5-turbo

    mentions of clothing and apparel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xi
    -0.73
    =-=-=-=-
    -0.64
    Published
    -0.64
    gom
    -0.63
    ived
    -0.63
    stro
    -0.62
    Remote
    -0.62
     Kong
    -0.61
    OUNT
    -0.61
    uth
    -0.60
    POSITIVE LOGITS
     clothing
    3.60
     Clothing
    2.88
     apparel
    2.70
     clothes
    2.43
     garments
    2.32
     footwear
    2.11
     garment
    2.00
     attire
    1.99
     underwear
    1.81
     jewelry
    1.73
    Activations Density 0.013%

    No Known Activations