© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 22112
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    100
    +0.12
    0.5%
    404
    +0.11
    0.5%
    672
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.03
    153
    +0.11
    0.02
    627
    +0.10
    0.02
    Negative Logits
    inventoryQuantity
    -0.77
     tug
    -0.72
     scaven
    -0.71
     chang
    -0.71
    EStreamFrame
    -0.71
     Sou
    -0.70
     Clim
    -0.69
     Conver
    -0.68
     sou
    -0.68
     transf
    -0.67
    POSITIVE LOGITS
    61
    1.27
    63
    1.24
    59
    1.24
    54
    1.24
     59
    1.23
    64
    1.23
    53
    1.23
    55
    1.23
    69
    1.21
    62
    1.21
    Activations Density 0.087%

    No Known Activations