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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1727
    Prev
    Next
    INDEX
    Explanations

    information related to sports matches and statistics

    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
    148
    +0.11
    0.5%
    543
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.11
    0.03
    600
    +0.10
    0.02
    412
    +0.10
    0.02
    Negative Logits
     Halls
    -0.68
     newsletters
    -0.68
     Lunar
    -0.67
     Alpha
    -0.66
    soDeliveryDate
    -0.65
     Postal
    -0.64
     Legisl
    -0.63
     respects
    -0.61
     Nort
    -0.61
     Kappa
    -0.60
    POSITIVE LOGITS
     batted
    0.81
    inki
    0.77
    productive
    0.68
     tallied
    0.68
    cussion
    0.68
     turnovers
    0.67
    brance
    0.67
     defensively
    0.67
    aleb
    0.66
    uracy
    0.66
    Activations Density 0.109%

    No Known Activations