© 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 24576
    9. 8-RES_FS24576-JB
    11. 7020
    Prev
    Next
    INDEX
    Explanations

    specific details related to governmental or administrative activities

    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
    480
    +0.45
    2.3%
    87
    +0.22
    1.1%
    447
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.45
    0.11
    480
    +0.22
    0.04
    288
    +0.18
    0.12
    Negative Logits
     awa
    -0.63
     tiss
    -0.49
    oooooooooooooooo
    -0.46
     glim
    -0.46
     rall
    -0.46
     nodd
    -0.45
    Mat
    -0.45
    mmmm
    -0.44
     showc
    -0.43
    cock
    -0.43
    POSITIVE LOGITS
    )?
    0.93
     ):
    0.74
    ,[
    0.72
     *)
    0.69
    )
    0.68
    ),
    0.66
     )
    0.65
    *)
    0.64
    )</
    0.63
    )[
    0.63
    Activations Density 1.203%

    No Known Activations