© 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 EvalsExportsAPI 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. 7538
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and government figures

    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
    314
    +0.13
    0.6%
    186
    +0.10
    0.5%
    720
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.13
    0.04
    718
    +0.10
    0.04
    617
    +0.10
    0.03
    Negative Logits
    ":[
    -0.66
    ':
    -0.66
    ascus
    -0.65
    Interest
    -0.64
    .....
    -0.61
    ciplinary
    -0.61
    .......
    -0.61
    "))
    -0.61
    âĢ¦..
    -0.58
    hend
    -0.58
    POSITIVE LOGITS
    !).
    1.24
    ?).
    1.22
    !),
    1.12
    ?),
    1.02
    !)
    0.97
    ?)
    0.95
    ).
    0.88
     ).
    0.88
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.83
    )?
    0.82
    Activations Density 0.817%

    No Known Activations