© 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 24576
    9. 8-RES_FS24576-JB
    11. 9949
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and statistical terms related to economics and metrics

    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
    497
    +0.11
    0.5%
    623
    +0.10
    0.5%
    39
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.11
    0.03
    623
    +0.10
    0.02
    725
    +0.10
    0.02
    Negative Logits
    kef
    -0.92
    artisan
    -0.88
    LESS
    -0.81
    wright
    -0.79
    uminati
    -0.79
    imore
    -0.78
    itsch
    -0.78
    enegger
    -0.77
    UTF
    -0.75
    warts
    -0.74
    POSITIVE LOGITS
    ized
    1.16
     income
    1.11
     incomes
    1.04
     earnings
    1.01
     wage
    1.00
     averages
    0.99
     revenue
    0.94
     installments
    0.94
     increments
    0.93
     allowance
    0.93
    Activations Density 0.051%

    No Known Activations