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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 3771
    Prev
    Next
    INDEX
    Explanations

    economic terms related to money and national finance

    oai_token-act-pair · gpt-3.5-turbo

    references to "gross" or economic metrics related to gross domestic product (GDP)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wark
    -0.78
    quickShipAvailable
    -0.71
    ournal
    -0.70
     Spit
    -0.67
    pires
    -0.66
     Aval
    -0.65
     Buckingham
    -0.64
     Brock
    -0.62
     Abbey
    -0.62
     Chains
    -0.61
    POSITIVE LOGITS
     receipts
    0.97
    ewater
    0.97
    es
    0.86
     negligence
    0.84
     margins
    0.82
     domestic
    0.80
    er
    0.79
    ed
    0.79
    edly
    0.77
    hest
    0.77
    Activations Density 0.024%

    No Known Activations