© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14594
    Prev
    Next
    INDEX
    Explanations

    references to financial terms and metrics, specifically focusing on terms related to economic indicators like gross domestic product (GDP) and debt

    oai_token-act-pair · gpt-3.5-turbo

    references to "gross" metrics related to economic indicators and statistics

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

    No Comments

    Negative Logits
    attled
    -0.77
    ournal
    -0.73
     Buckingham
    -0.70
    chers
    -0.67
     accomp
    -0.67
     challeng
    -0.67
     COUR
    -0.66
     Franç
    -0.62
    cknowled
    -0.60
    pire
    -0.60
    POSITIVE LOGITS
     gross
    0.94
    gross
    0.91
     receipts
    0.85
    es
    0.83
    hest
    0.79
    cre
    0.78
     Gross
    0.75
    ewater
    0.72
    itarian
    0.71
     disproportion
    0.69
    Activations Density 0.012%

    No Known Activations