© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    mentions of significant consequences or impacts

    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
    +0.16
    0.7%
    414
    +0.10
    0.4%
    481
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.16
    0.03
    414
    +0.10
    0.02
    528
    +0.10
    0.02
    Negative Logits
    aniel
    -0.85
    wine
    -0.78
    lists
    -0.77
    BuyableInstoreAndOnline
    -0.74
    oof
    -0.72
    VPN
    -0.71
    chool
    -0.71
    LEY
    -0.71
    eas
    -0.69
    atican
    -0.68
    POSITIVE LOGITS
     morale
    1.21
    erous
    1.01
     profitability
    0.99
     perceptions
    0.92
     shaping
    0.91
     circulation
    0.91
     perception
    0.91
     productivity
    0.90
     humanity
    0.89
     competitiveness
    0.86
    Activations Density 0.106%

    No Known Activations