© 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. 7774
    Prev
    Next
    INDEX
    Explanations

    mention instances of negation or exclusion

    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
    420
    +0.11
    0.5%
    100
    +0.11
    0.5%
    61
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.11
    0.05
    620
    +0.11
    0.04
    643
    +0.11
    0.04
    Negative Logits
    soType
    -0.74
     Calculator
    -0.65
     Archive
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    ON
    -0.63
    FAQ
    -0.63
    ISM
    -0.63
    OST
    -0.62
    issance
    -0.61
     Statements
    -0.61
    POSITIVE LOGITS
     necessarily
    1.07
     otherwise
    0.99
     ordinarily
    0.99
    fit
    0.92
     normally
    0.88
     traditionally
    0.87
    necess
    0.86
     conform
    0.86
     previously
    0.86
    icable
    0.83
    Activations Density 0.196%

    No Known Activations