© 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 EvalsExportsinterp-engineNEWAPI 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. 14179
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and events

    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
    667
    +0.10
    0.4%
    488
    +0.09
    0.4%
    675
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.10
    0.09
    37
    +0.09
    0.07
    48
    +0.09
    0.07
    Negative Logits
     jugg
    -0.67
     popularity
    -0.65
     snail
    -0.64
     superpower
    -0.63
     range
    -0.63
     presets
    -0.62
     habit
    -0.61
     downs
    -0.61
     handy
    -0.61
     colonies
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.00
    efe
    0.90
    ONSORED
    0.88
    said
    0.84
    ¯
    0.80
    east
    0.79
    while
    0.78
    his
    0.78
    then
    0.77
    ername
    0.72
    Activations Density 0.221%

    No Known Activations