© 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 49152
    9. 8-RES_FS49152-JB
    11. 45832
    Prev
    Next
    INDEX
    Explanations

    references to rounds in a draft context, particularly in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    157
    +0.12
    0.5%
    302
    +0.11
    0.5%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.12
    0.02
    752
    +0.11
    0.02
    157
    +0.10
    0.02
    Negative Logits
    sth
    -0.92
     Wem
    -0.79
     ful
    -0.76
     tempor
    -0.73
    beh
    -0.71
    uras
    -0.70
     Hast
    -0.69
     estab
    -0.69
    accompanied
    -0.69
    reason
    -0.68
    POSITIVE LOGITS
    Draft
    1.00
     draft
    0.90
     picks
    0.89
     pick
    0.88
    士
    0.86
     rookie
    0.84
     Draft
    0.83
     lottery
    0.82
    backer
    0.81
     rob
    0.80
    Activations Density 0.012%

    No Known Activations