© 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 24576
    9. 8-RES_FS24576-JB
    11. 8690
    Prev
    Next
    INDEX
    Explanations

    mentions of the FOX Sports network

    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
    159
    +0.13
    0.6%
    276
    +0.11
    0.5%
    268
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.13
    0.01
    276
    +0.11
    0.01
    736
    +0.10
    0.01
    Negative Logits
    abee
    -0.88
     Edison
    -0.79
    ency
    -0.75
    hot
    -0.75
    ivari
    -0.73
    ammy
    -0.73
    itance
    -0.73
    orders
    -0.73
    aca
    -0.71
    ylum
    -0.71
    POSITIVE LOGITS
    CAST
    1.23
     SPORTS
    1.07
    FOX
    0.98
    IUM
    0.95
    OUT
    0.92
    WOOD
    0.92
    DEN
    0.90
    EXT
    0.90
    DEF
    0.88
    PLAY
    0.86
    Activations Density 0.011%

    No Known Activations