© 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. 22713
    Prev
    Next
    INDEX
    Explanations

    references to governmental or legislative actions and regulations

    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
    393
    +0.18
    0.9%
    159
    +0.15
    0.7%
    385
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.18
    0.12
    362
    +0.15
    0.12
    608
    +0.14
    0.12
    Negative Logits
    Ò
    -0.92
    thood
    -0.90
    qi
    -0.78
    obyl
    -0.77
    ustom
    -0.75
     whilst
    -0.74
    antes
    -0.73
    æĹ
    -0.72
    ãĥĺ
    -0.72
    ça
    -0.70
    POSITIVE LOGITS
     agency
    1.18
     latter
    1.18
     remainder
    1.14
     Legislature
    1.10
     Department
    1.10
     feds
    1.10
     legislature
    1.09
    oret
    1.09
     bureau
    1.05
     commissioner
    1.04
    Activations Density 0.557%

    No Known Activations