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. 1-RES-JB
    6. 19716
    Prev
    Next
    INDEX
    Explanations

    words related to fashion

    oai_token-act-pair · gpt-3.5-turbo

    references to fashion and its related concepts

    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
     Hemp
    -0.79
    JV
    -0.75
     Liqu
    -0.67
     Barton
    -0.65
     sher
    -0.65
    Torrent
    -0.64
     Ezek
    -0.63
     Watching
    -0.63
    ramid
    -0.62
     Sau
    -0.61
    POSITIVE LOGITS
     fashion
    1.17
    fashion
    1.08
     Fashion
    0.97
    ably
    0.91
    ashion
    0.84
    ienne
    0.83
    ables
    0.83
     apparel
    0.82
     cout
    0.80
    soDeliveryDate
    0.78
    Activations Density 0.007%

    No Known Activations