© 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. 8831
    Prev
    Next
    INDEX
    Explanations

    phrases related to documents, censorship, vulnerability, market reactions, and testing

    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
    +0.27
    1.3%
    480
    +0.12
    0.6%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.27
    0.01
    97
    +0.12
    0.04
    714
    +0.10
    0.04
    Negative Logits
    ãĤ´ãĥ³
    -0.78
     respectively
    -0.68
    .).
    -0.62
    ?).
    -0.62
    Reviewed
    -0.60
    $.
    -0.56
    .(
    -0.56
     «
    -0.53
     "-
    -0.53
    REDACTED
    -0.53
    POSITIVE LOGITS
     ..."
    1.38
    %"
    1.38
    ),"
    1.37
    ,"
    1.33
     âĢ¦"
    1.31
    )"
    1.26
    )",
    1.26
    ,'"
    1.26
    .")
    1.25
    ',"
    1.20
    Activations Density 1.685%

    No Known Activations