© 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. 831
    Prev
    Next
    INDEX
    Explanations

    burger recipes

    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
    385
    +0.10
    0.5%
    645
    +0.09
    0.4%
    449
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.03
    26
    +0.09
    0.03
    659
    +0.09
    0.03
    Negative Logits
    words
    -0.90
    âĢ¢âĢ¢
    -0.79
     lobe
    -0.72
    fty
    -0.69
    pend
    -0.62
    boards
    -0.61
     Mi
    -0.59
    xus
    -0.58
    board
    -0.58
    word
    -0.56
    POSITIVE LOGITS
    undy
    1.40
    lar
    1.16
    atory
    1.04
    roup
    1.02
    raphics
    1.00
    raph
    0.97
    raphic
    0.96
    sburgh
    0.95
    ues
    0.94
    dor
    0.91
    Activations Density 0.122%

    No Known Activations