© 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 12288
    9. 8-RES_FS12288-JB
    11. 10824
    Prev
    Next
    INDEX
    Explanations

    technical terms related to research, feedback, and evaluation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    87
    +0.41
    2.4%
    481
    +0.13
    0.8%
    447
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.41
    -0.02
    659
    +0.13
    0.08
    176
    +0.09
    0.04
    Negative Logits
     thereto
    -0.55
     thereof
    -0.54
     respectively
    -0.53
     âĢ¦"
    -0.52
     encomp
    -0.49
     corresponding
    -0.49
     otherwise
    -0.49
     latter
    -0.49
    .","
    -0.47
     nearby
    -0.47
    POSITIVE LOGITS
     References
    0.75
     Profile
    0.75
     Versus
    0.74
     Functions
    0.71
     Differences
    0.71
    ibliography
    0.71
     Comparison
    0.70
     Overview
    0.68
     Thoughts
    0.68
     Recommend
    0.68
    Activations Density 1.193%

    No Known Activations