© 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. 1921
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical figures

    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
    132
    +0.10
    0.4%
    55
    +0.09
    0.4%
    573
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.10
    0.02
    55
    +0.09
    0.02
    726
    +0.09
    0.02
    Negative Logits
    Austral
    -0.64
    enf
    -0.61
    article
    -0.59
    ger
    -0.58
    lic
    -0.57
    Something
    -0.56
    eness
    -0.56
    bor
    -0.56
    ggles
    -0.56
    talk
    -0.56
    POSITIVE LOGITS
    .,
    0.72
     comprising
    0.70
    é¾įåĸļ士
    0.70
     situated
    0.67
     proport
    0.65
    eatures
    0.64
    .).
    0.64
    .;
    0.64
    GROUP
    0.64
     guiIcon
    0.62
    Activations Density 0.093%

    No Known Activations