© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 555
    Prev
    Next
    INDEX
    Explanations

    names of individuals and organizations

    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
    87
    +0.20
    1.0%
    432
    +0.09
    0.4%
    447
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.20
    -0.05
    718
    +0.09
    0.08
    189
    +0.08
    0.06
    Negative Logits
    !'
    -0.87
    !'"
    -0.68
    ?'
    -0.65
    )'
    -0.64
    .'
    -0.63
    .ãĢį
    -0.59
    .--
    -0.59
    ').
    -0.59
    .—
    -0.57
    ?'"
    -0.56
    POSITIVE LOGITS
     "[
    0.99
     "â̦
    0.95
     "
    0.93
     "'
    0.92
     "...
    0.90
     anecd
    0.82
     "#
    0.81
     "(
    0.80
     ''
    0.70
     misinterpret
    0.70
    Activations Density 1.942%

    No Known Activations