© 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 EvalsExportsinterp-engineNEWAPI 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. 2679
    Prev
    Next
    INDEX
    Explanations

    references to the flow of something, particularly in technical or scientific contexts

    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
    +0.11
    0.5%
    195
    +0.10
    0.5%
    106
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.11
    0.02
    288
    +0.10
    0.02
    439
    +0.10
    0.01
    Negative Logits
     scratched
    -0.68
    DonaldTrump
    -0.66
     Bav
    -0.66
     SAY
    -0.65
    andals
    -0.63
     leveled
    -0.63
     à¨
    -0.62
     nailed
    -0.59
     citiz
    -0.59
     Ladies
    -0.59
    POSITIVE LOGITS
    chart
    1.32
    flow
    0.99
    flows
    0.94
    through
    0.93
    stream
    0.91
     flows
    0.90
    rates
    0.86
    waters
    0.86
     flowing
    0.85
    ered
    0.85
    Activations Density 0.036%

    No Known Activations