© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1322
    Prev
    Next
    INDEX
    Explanations

    sport-related events, particularly focusing on plays, scores, and game outcomes

    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
    481
    +0.15
    0.7%
    460
    +0.12
    0.5%
    384
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.15
    0.05
    651
    +0.12
    0.04
    412
    +0.11
    0.04
    Negative Logits
    itarian
    -0.87
    chwitz
    -0.82
    sonian
    -0.80
    anamo
    -0.73
    netflix
    -0.70
    ilial
    -0.66
    agate
    -0.65
     anecd
    -0.65
    DragonMagazine
    -0.64
    Reviewed
    -0.64
    POSITIVE LOGITS
     halftime
    0.91
    ftime
    0.90
     stopp
    0.85
     opener
    0.84
     kickoff
    0.78
     replay
    0.74
    kick
    0.73
     scoreboard
    0.71
     pandemonium
    0.69
    imester
    0.69
    Activations Density 0.167%

    No Known Activations