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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 2989
    Prev
    Next
    INDEX
    Explanations

    items of clothing, particularly jeans and denim-related items

    oai_token-act-pair · gpt-3.5-turbo

    references to jeans and denim clothing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atively
    -1.06
    alling
    -0.85
    heastern
    -0.84
    orah
    -0.81
    grave
    -0.80
    emis
    -0.79
    ahi
    -0.79
    rican
    -0.78
    herical
    -0.78
    iatrics
    -0.77
    POSITIVE LOGITS
     jeans
    0.97
     denim
    0.79
    sters
    0.78
    suit
    0.73
    mer
    0.70
    ster
    0.66
    mers
    0.66
     Mustang
    0.65
     Manson
    0.65
     Bee
    0.63
    Activations Density 0.050%

    No Known Activations