© 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 EvalsExportsinterp-engineNEWAPI 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. 22330
    Prev
    Next
    INDEX
    Explanations

    references to tax codes and related legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered 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
    100
    +0.11
    0.5%
    120
    +0.10
    0.5%
    234
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.11
    0.02
    639
    +0.10
    0.02
    81
    +0.09
    0.01
    Negative Logits
    onen
    -0.80
    ovie
    -0.77
    voy
    -0.76
    idon
    -0.75
    lock
    -0.73
    abal
    -0.72
    skirts
    -0.71
    oday
    -0.69
     Archdemon
    -0.69
    anton
    -0.67
    POSITIVE LOGITS
     nonprofit
    0.78
    entity
    0.76
     nonprofits
    0.72
    exempt
    0.71
    ivable
    0.71
    DIV
    0.69
    Merit
    0.69
     insured
    0.68
     nond
    0.65
    fund
    0.65
    Activations Density 0.060%

    No Known Activations