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

    Neuronpedia

    Jacobian LensNEW
    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. 7002
    Prev
    Next
    INDEX
    Explanations

    phrases related to large financial figures like "dollar billion" and "euro."

    oai_token-act-pair · gpt-3.5-turbo

    references to large financial amounts and economic metrics

    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
    odox
    -0.83
     Skydragon
    -0.69
     Templ
    -0.68
     Samurai
    -0.67
     Sorce
    -0.65
    nesday
    -0.63
    eda
    -0.63
     Jackets
    -0.62
     Cron
    -0.61
    deck
    -0.59
    POSITIVE LOGITS
     dollars
    0.99
     USD
    0.88
    USD
    0.86
     billions
    0.77
     Dollars
    0.75
     millionaires
    0.73
     pounds
    0.73
    dollar
    0.73
     trillions
    0.73
     worth
    0.71
    Activations Density 0.164%

    No Known Activations