© 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. 10990
    Prev
    Next
    INDEX
    Explanations

    tutorials and instructional content related to various technical topics

    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
    679
    +0.13
    0.6%
    620
    +0.12
    0.6%
    644
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.13
    0.02
    620
    +0.12
    0.01
    644
    +0.12
    0.02
    Negative Logits
    olls
    -0.76
    olitics
    -0.75
    cffff
    -0.73
    polit
    -0.68
    ergic
    -0.68
    oples
    -0.67
    itol
    -0.65
    ãĥĥãĥī
    -0.64
    och
    -0.64
    yss
    -0.62
    POSITIVE LOGITS
     tutorials
    0.93
     tutorial
    0.91
     COUR
    0.88
     Tutorial
    0.87
     Guide
    0.87
     guide
    0.85
    STEP
    0.84
     guides
    0.83
     videos
    0.79
     Guides
    0.78
    Activations Density 0.036%

    No Known Activations