© 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. 22298
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "some"

    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
    608
    +0.14
    0.6%
    393
    +0.13
    0.6%
    337
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.14
    0.05
    608
    +0.13
    0.05
    392
    +0.12
    0.05
    Negative Logits
    SPONSORED
    -0.91
    ean
    -0.70
    gon
    -0.68
    istan
    -0.67
    ip
    -0.66
    vest
    -0.66
    gi
    -0.65
    âĢ¢âĢ¢
    -0.64
    raid
    -0.62
    istar
    -0.62
    POSITIVE LOGITS
    place
    1.26
    body
    0.99
    ones
    0.97
     semblance
    0.97
     serious
    0.89
     nifty
    0.85
     sort
    0.84
     additional
    0.82
     tasty
    0.81
    how
    0.81
    Activations Density 0.086%

    No Known Activations