© 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. 8533
    Prev
    Next
    INDEX
    Explanations

    the word "grab" or similar terms indicating physical seizing or taking hold of something

    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
    241
    +0.12
    0.6%
    677
    +0.09
    0.4%
    366
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.12
    0.02
    366
    +0.09
    0.02
    569
    +0.08
    0.02
    Negative Logits
    AMY
    -0.77
    xual
    -0.74
    SPONSORED
    -0.65
    present
    -0.65
    MQ
    -0.64
    ema
    -0.64
    acre
    -0.64
     Prol
    -0.62
    ingen
    -0.62
    ————
    -0.61
    POSITIVE LOGITS
     onto
    0.98
    bable
    0.94
    bers
    0.93
    bing
    0.90
     hold
    0.90
    hold
    0.86
     glances
    0.80
    ber
    0.78
    reau
    0.75
    bage
    0.75
    Activations Density 0.044%

    No Known Activations