© 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 12288
    9. 8-RES_FS12288-JB
    11. 10734
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    36
    +0.31
    1.5%
    250
    +0.12
    0.6%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.31
    0.15
    250
    +0.12
    0.07
    263
    +0.11
    0.06
    Negative Logits
    Edit
    -0.68
     ATK
    -0.66
     Assistance
    -0.65
     Alphabet
    -0.64
     Esports
    -0.61
     Ampl
    -0.61
     Umb
    -0.60
     advances
    -0.60
     eSports
    -0.60
    End
    -0.59
    POSITIVE LOGITS
    rouse
    1.18
    uras
    1.07
     lot
    1.06
    ria
    1.00
     few
    0.98
    sembly
    0.98
    cess
    0.97
    pron
    0.97
    vez
    0.94
     tad
    0.94
    Activations Density 0.386%

    No Known Activations