© 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. 24488
    Prev
    Next
    INDEX
    Explanations

    names, particularly those of individuals

    oai_token-act-pair · gpt-4o-miniTriggered 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
    659
    +0.12
    0.5%
    631
    +0.11
    0.5%
    2
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.05
    232
    +0.11
    0.03
    525
    +0.09
    0.03
    Negative Logits
    imately
    -0.72
    ï¸ı
    -0.67
    vous
    -0.66
     broom
    -0.65
    yip
    -0.65
    ashtra
    -0.64
     LEDs
    -0.62
     gem
    -0.60
    >>\
    -0.59
     Petr
    -0.57
    POSITIVE LOGITS
    canon
    0.70
    asley
    0.67
    mberg
    0.66
    ukes
    0.65
    Marsh
    0.65
    emen
    0.65
    oyer
    0.63
    mann
    0.61
    iquette
    0.60
    construct
    0.60
    Activations Density 0.073%

    No Known Activations