© 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 3072
    9. 8-RES_FS3072-JB
    11. 70
    Prev
    Next
    INDEX
    Explanations

    complex statements discussing various social and global issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    393
    +0.25
    1.2%
    362
    +0.23
    1.1%
    608
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.25
    0.27
    608
    +0.23
    0.23
    393
    +0.18
    0.19
    Negative Logits
     besides
    -0.80
     namely
    -0.79
    SPONSORED
    -0.74
    tackle
    -0.71
     without
    -0.71
    bg
    -0.70
     wherein
    -0.69
    elaide
    -0.69
     with
    -0.69
    thood
    -0.68
    POSITIVE LOGITS
     possibility
    1.41
     notion
    1.29
     entirety
    1.26
     slightest
    1.26
     extent
    1.25
     latter
    1.22
     fact
    1.17
     importance
    1.17
     idea
    1.17
     aforementioned
    1.13
    Activations Density 2.109%

    No Known Activations