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. 11056
    Prev
    Next
    INDEX
    Explanations

    keywords related to economic indicators, particularly focusing on gross domestic product (GDP)

    oai_token-act-pair · gpt-3.5-turbo

    references to gross domestic product and related economic metrics

    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
    attled
    -0.75
    chers
    -0.70
     Buckingham
    -0.67
     COUR
    -0.66
    ournal
    -0.64
    Downloadha
    -0.64
    uador
    -0.63
     Skydragon
    -0.63
     Hosp
    -0.62
     Tsarnaev
    -0.61
    POSITIVE LOGITS
     gross
    0.98
    gross
    0.93
     receipts
    0.82
    es
    0.81
    ewater
    0.76
    hest
    0.73
    esy
    0.73
    cre
    0.70
    ling
    0.69
     disproportion
    0.68
    Activations Density 0.011%

    No Known Activations