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

    Neuronpedia

    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 12288
    9. 8-RES_FS12288-JB
    11. 1705
    Prev
    Next
    INDEX
    Explanations

    references to the name "Allen"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    183
    +0.12
    0.5%
    220
    +0.11
    0.5%
    377
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.12
    0.02
    659
    +0.11
    0.02
    525
    +0.11
    0.02
    Negative Logits
    anooga
    -0.88
    */(
    -0.88
    kered
    -0.87
    ulates
    -0.87
    ounty
    -0.81
    ceed
    -0.80
    ornia
    -0.78
    ulate
    -0.77
    urnal
    -0.75
    hops
    -0.73
    POSITIVE LOGITS
     Dull
    1.09
     Gins
    0.96
    ham
    0.85
     Robinson
    0.83
    hurst
    0.79
     Hamm
    0.78
    wall
    0.78
    stown
    0.78
     Allen
    0.77
     Poe
    0.76
    Activations Density 0.088%

    No Known Activations