© 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. 9099
    Prev
    Next
    INDEX
    Explanations

    dates and times in the format "month day, year, hour:minute AM/PM GMT"

    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
    311
    +0.14
    0.6%
    231
    +0.11
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.14
    0.01
    311
    +0.11
    0.01
    259
    +0.10
    0.01
    Negative Logits
    pton
    -0.74
    ffield
    -0.69
    duct
    -0.66
    kus
    -0.66
    bor
    -0.65
    Kin
    -0.63
    pha
    -0.63
    tons
    -0.62
    ston
    -0.62
    ciation
    -0.62
    POSITIVE LOGITS
    /+
    0.83
     (+
    0.81
     GMT
    0.80
    +
    0.76
     Entry
    0.72
    ARGET
    0.69
     CET
    0.67
    agascar
    0.67
     (-
    0.67
    +.
    0.65
    Activations Density 0.007%

    No Known Activations