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. 3-RES-JB
    6. 10515
    Prev
    Next
    INDEX
    Explanations

    the word "eBay"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of online marketplaces and platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.72
     Archdemon
    -0.70
    arios
    -0.69
     Freed
    -0.66
    NEY
    -0.64
     Bav
    -0.62
     Eston
    -0.62
     Lithuan
    -0.60
    ãĥ´
    -0.59
     Churchill
    -0.59
    POSITIVE LOGITS
     auctions
    0.88
     sellers
    0.80
     seller
    0.79
     listings
    0.75
     eBay
    0.73
    ModLoader
    0.73
    Ĥİ
    0.71
    ogle
    0.70
     invoice
    0.70
     postings
    0.70
    Activations Density 0.004%

    No Known Activations