© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    proper names of people or entities, particularly names starting with lowercase letters

    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
    447
    +0.14
    0.6%
    288
    +0.10
    0.5%
    199
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.06
    224
    +0.10
    0.05
    659
    +0.10
    0.05
    Negative Logits
    izen
    -0.85
    pter
    -0.82
    fare
    -0.80
    rous
    -0.77
    ered
    -0.76
    istically
    -0.76
    ishers
    -0.76
    zzi
    -0.74
    aji
    -0.73
    acts
    -0.73
    POSITIVE LOGITS
    hip
    1.17
    '
    1.14
    hips
    1.12
    ullivan
    0.99
    ource
    0.94
    manship
    0.93
    ']
    0.90
    burgh
    0.90
    chwitz
    0.87
    hift
    0.87
    Activations Density 0.202%

    No Known Activations