© 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. 16609
    Prev
    Next
    INDEX
    Explanations

    references to legislative bills and reforms, specifically related to electronic communications and privacy acts

    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
    447
    +0.13
    0.6%
    524
    +0.10
    0.4%
    181
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.13
    0.03
    181
    +0.10
    0.03
    343
    +0.10
    0.02
    Negative Logits
     Acer
    -0.90
    leon
    -0.81
    iston
    -0.75
    ij士
    -0.75
     Cater
    -0.73
     Yi
    -0.70
    pring
    -0.69
     Bucc
    -0.68
     Fiesta
    -0.68
    cam
    -0.68
    POSITIVE LOGITS
     Amendments
    1.11
     legislation
    1.07
     repeal
    1.04
     waivers
    1.01
     protections
    0.97
     recipients
    0.97
     regulations
    0.96
     reforms
    0.95
     enforcement
    0.93
     mandates
    0.92
    Activations Density 0.081%

    No Known Activations