© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 15517
    Prev
    Next
    INDEX
    Explanations

    economic terms related to the financial sector

    oai_token-act-pair · gpt-3.5-turbo

    references to economic metrics, specifically 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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Buckingham
    -0.71
    attled
    -0.69
    quickShipAvailable
    -0.67
    ournal
    -0.67
    odic
    -0.64
     therap
    -0.63
     Franç
    -0.62
    pires
    -0.61
     whim
    -0.60
    atter
    -0.60
    POSITIVE LOGITS
    ewater
    0.89
     receipts
    0.88
    gross
    0.83
    es
    0.82
     gross
    0.81
    hest
    0.78
    cre
    0.70
    itarian
    0.69
    nih
    0.68
     Domestic
    0.68
    Activations Density 0.024%

    No Known Activations