© 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. 879
    Prev
    Next
    INDEX
    Explanations

    discussions related to technology and advancements

    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
    393
    +0.10
    0.5%
    66
    +0.10
    0.5%
    59
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.06
    546
    +0.10
    0.06
    66
    +0.10
    0.06
    Negative Logits
    pec
    -0.68
    rolet
    -0.67
    YC
    -0.66
    rossover
    -0.63
    von
    -0.63
    AKING
    -0.62
    oo
    -0.61
    SB
    -0.61
     msec
    -0.61
    quist
    -0.61
    POSITIVE LOGITS
     however
    1.04
     there
    0.87
     we
    0.83
     which
    0.77
     it
    0.74
     moreover
    0.73
    there
    0.72
     meanwhile
    0.71
     whereby
    0.69
     they
    0.67
    Activations Density 0.363%

    No Known Activations