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. 10522
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of clothing, particularly shoes

    oai_token-act-pair · gpt-3.5-turbo

    references to shoes in various contexts

    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
    atom
    -0.76
    count
    -0.67
     Population
    -0.63
     Corpus
    -0.63
    rate
    -0.62
    CT
    -0.61
     contained
    -0.61
    urg
    -0.61
    uld
    -0.60
    arat
    -0.60
    POSITIVE LOGITS
     shoes
    3.87
     Shoes
    2.95
     footwear
    2.56
     sneakers
    2.53
     boots
    2.33
     shoe
    2.22
     socks
    2.03
     heels
    1.74
     jeans
    1.69
     gloves
    1.68
    Activations Density 0.020%

    No Known Activations