© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 24576
    9. 8-RES_FS24576-JB
    11. 9147
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms or descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    556
    +0.10
    0.5%
    160
    +0.10
    0.4%
    292
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.10
    0.08
    292
    +0.10
    0.08
    182
    +0.09
    0.08
    Negative Logits
     Scenes
    -0.68
     Jub
    -0.67
     Mobil
    -0.64
     Quarterly
    -0.64
     Samar
    -0.64
     Banner
    -0.62
     succession
    -0.62
     Showdown
    -0.61
     Polk
    -0.61
     Seym
    -0.61
    POSITIVE LOGITS
    s
    1.00
    ses
    0.98
    ved
    0.95
    ï¸ı
    0.95
    felt
    0.94
    should
    0.94
    ttle
    0.92
    agree
    0.91
    ti
    0.90
    lishes
    0.88
    Activations Density 0.245%

    No Known Activations