© 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. 18481
    Prev
    Next
    INDEX
    Explanations

    code snippets related to database operations

    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
    158
    +0.12
    0.5%
    96
    +0.12
    0.5%
    63
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.03
    158
    +0.12
    0.04
    96
    +0.10
    0.03
    Negative Logits
     guiName
    -0.73
     differe
    -0.71
    accompan
    -0.70
     defic
    -0.64
    [/
    -0.64
    jri
    -0.63
    ilater
    -0.63
     Nare
    -0.63
     appe
    -0.62
    STER
    -0.62
    POSITIVE LOGITS
    ))
    1.50
    ){
    1.50
    )"
    1.46
    )
    1.38
    );
    1.35
    )/
    1.31
    ));
    1.30
    ):
    1.30
    ())
    1.30
    )(
    1.29
    Activations Density 0.080%

    No Known Activations