© 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. 10849
    Prev
    Next
    INDEX
    Explanations

    words related to health, physiology, dietary habits, and financial terms like income and prices

    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
    76
    +0.09
    0.4%
    439
    +0.09
    0.4%
    523
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.08
    439
    +0.09
    0.06
    575
    +0.09
    0.06
    Negative Logits
     Poe
    -0.77
     Sporting
    -0.74
     Flesh
    -0.74
    bsite
    -0.71
    enegger
    -0.69
    aughs
    -0.69
     Aven
    -0.68
    £ı
    -0.68
     Petra
    -0.67
     Movie
    -0.66
    POSITIVE LOGITS
     suppression
    1.04
     manipulation
    1.02
     consolidation
    1.01
     aggregation
    1.01
     allocation
    0.99
    less
    0.98
     disruption
    0.97
     redistribution
    0.95
     imbalance
    0.94
     accumulation
    0.93
    Activations Density 0.361%

    No Known Activations