© 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. 11061
    Prev
    Next
    INDEX
    Explanations

    information about contests, updates, and announcements

    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
    640
    +0.29
    1.4%
    480
    +0.19
    0.9%
    447
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.13
    160
    +0.19
    0.12
    107
    +0.16
    0.10
    Negative Logits
     displacement
    -0.91
     eroded
    -0.84
     territorial
    -0.81
     displaced
    -0.80
     overt
    -0.80
     tape
    -0.80
     nonexistent
    -0.80
     grop
    -0.79
     herself
    -0.78
     increasingly
    -0.78
    POSITIVE LOGITS
    Thank
    1.47
    Feel
    1.39
    Features
    1.39
    Please
    1.38
    PLE
    1.38
    Have
    1.37
    Welcome
    1.37
    Download
    1.36
    Enjoy
    1.35
    Disclaimer
    1.35
    Activations Density 0.324%

    No Known Activations