© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 17939
    Prev
    Next
    INDEX
    Explanations

    phrases related to taxpayer money or funding

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.13
    0.6%
    488
    +0.13
    0.6%
    615
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.13
    0.02
    509
    +0.13
    0.01
    66
    +0.12
    0.02
    Negative Logits
    lime
    -0.73
     Signal
    -0.68
     Styles
    -0.68
     Bolt
    -0.68
    Church
    -0.65
     Templ
    -0.63
    azi
    -0.62
    quickShipAvailable
    -0.62
     Whip
    -0.61
     Totem
    -0.61
    POSITIVE LOGITS
    payers
    1.25
     subsid
    1.19
    payer
    1.15
     dollars
    1.15
     taxpayers
    1.13
     taxpayer
    1.07
     funded
    1.02
     subsidized
    0.96
     subsidy
    0.95
    funded
    0.94
    Activations Density 0.025%

    No Known Activations