© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9518
    Prev
    Next
    INDEX
    Explanations

    mentioned software versions

    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
    679
    +0.11
    0.5%
    30
    +0.09
    0.4%
    474
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.11
    0.03
    678
    +0.09
    0.03
    89
    +0.09
    0.03
    Negative Logits
    redo
    -0.86
    usters
    -0.83
    veyard
    -0.74
    ãĤī
    -0.72
     charism
    -0.72
     Skies
    -0.68
    oros
    -0.65
    umbai
    -0.65
    inently
    -0.64
    rib
    -0.64
    POSITIVE LOGITS
     thereof
    1.15
    UID
    0.92
    etting
    0.81
     of
    0.81
     version
    0.79
     versions
    0.75
    added
    0.74
     numbering
    0.73
    Versions
    0.71
    lihood
    0.69
    Activations Density 0.102%

    No Known Activations