© 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 12288
    9. 8-RES_FS12288-JB
    11. 9491
    Prev
    Next
    INDEX
    Explanations

    statements and discussions related to sports, team and player dynamics, and strategy

    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
    640
    +0.27
    1.3%
    255
    +0.11
    0.5%
    539
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.27
    0.12
    539
    +0.11
    0.07
    64
    +0.10
    -0.03
    Negative Logits
    boro
    -0.71
    andon
    -0.69
    ensibly
    -0.64
    senal
    -0.64
    inyl
    -0.64
    lections
    -0.63
     Reincarnated
    -0.63
    tones
    -0.63
     ideal
    -0.62
    minist
    -0.62
    POSITIVE LOGITS
    ONSORED
    0.91
    Write
    0.86
    METHOD
    0.82
    Correct
    0.81
    ³³³
    0.80
    Refer
    0.79
    Bus
    0.78
     Related
    0.77
    ³³³³
    0.76
    Newsletter
    0.74
    Activations Density 0.339%

    No Known Activations