Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24080
    Prev
    Next
    INDEX
    Explanations

    words related to shoes

    oai_token-act-pair · gpt-3.5-turbo

    references to shoes

    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
    sv
    -0.78
    urg
    -0.77
     sv
    -0.73
    rad
    -0.69
     Archdemon
    -0.69
    ASC
    -0.68
    bard
    -0.68
    ald
    -0.67
     Bots
    -0.67
    rika
    -0.66
    POSITIVE LOGITS
     shoe
    3.67
     footwear
    1.90
     shoes
    1.78
     sock
    1.56
     Shoes
    1.55
     sneakers
    1.52
     sne
    1.47
     garment
    1.46
     heel
    1.43
     sho
    1.41
    Activations Density 0.018%

    No Known Activations