© 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. 13836
    Prev
    Next
    INDEX
    Explanations

    actions related to following step-by-step instructions

    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
    481
    +0.14
    0.6%
    55
    +0.11
    0.5%
    16
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.14
    0.03
    125
    +0.11
    0.03
    274
    +0.11
    0.03
    Negative Logits
    é¾įå¥ij士
    -0.78
    yip
    -0.64
    RESULTS
    -0.64
    MAL
    -0.63
     Flavoring
    -0.63
    ãĥ´ãĤ¡
    -0.63
    icipated
    -0.62
    ierre
    -0.62
    é¾įå
    -0.61
    asel
    -0.61
    POSITIVE LOGITS
     by
    0.93
     upon
    0.84
     BY
    0.84
     prominently
    0.74
     alongside
    0.74
     anew
    0.71
     therein
    0.70
     throughout
    0.70
    abouts
    0.69
     squarely
    0.69
    Activations Density 0.147%

    No Known Activations