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

    Neuronpedia

    Jacobian LensNEW
    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. 9079
    Prev
    Next
    INDEX
    Explanations

    mentions of sports statistics and player performance

    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
    188
    +0.12
    0.5%
    668
    +0.11
    0.5%
    450
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    668
    +0.12
    0.04
    188
    +0.11
    0.04
    450
    +0.10
    0.03
    Negative Logits
     mobil
    -0.77
     organisers
    -0.74
     sponsoring
    -0.73
    mission
    -0.72
     postp
    -0.71
     envis
    -0.71
     Malaysia
    -0.70
     administration
    -0.67
     appointed
    -0.67
     organise
    -0.66
    POSITIVE LOGITS
     averaging
    1.15
     averaged
    1.14
     averages
    1.13
     Adjusted
    1.01
    Percent
    0.99
     regress
    0.98
    Stats
    0.96
     teammate
    0.95
     statistically
    0.95
    adjusted
    0.94
    Activations Density 0.447%

    No Known Activations