© 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. 6359
    Prev
    Next
    INDEX
    Explanations

    historical information or biographies of political figures

    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
    373
    +0.18
    0.9%
    314
    +0.13
    0.6%
    726
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.18
    -0.02
    701
    +0.13
    0.04
    284
    +0.09
    0.04
    Negative Logits
     Rac
    -0.84
     Day
    -0.76
     Tours
    -0.76
     Solutions
    -0.74
     Extras
    -0.73
     Universities
    -0.72
     Cookies
    -0.70
     Inc
    -0.69
     Disorder
    -0.69
     Month
    -0.68
    POSITIVE LOGITS
    iest
    1.33
    liest
    1.19
    osphere
    1.05
    hest
    1.03
    agonist
    1.00
    ciation
    0.98
    icter
    0.94
    emonic
    0.92
    istance
    0.89
    inous
    0.87
    Activations Density 0.181%

    No Known Activations