© 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 EvalsExportsinterp-engineNEWAPI 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. 16389
    Prev
    Next
    INDEX
    Explanations

    words related to legislation and construction

    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
    447
    +0.43
    2.3%
    480
    +0.28
    1.5%
    420
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.43
    -0.02
    585
    +0.28
    0.06
    267
    +0.11
    0.05
    Negative Logits
    Freedom
    -0.60
    wcs
    -0.51
    0000000000000000
    -0.50
    ascar
    -0.49
     doorstep
    -0.47
    Content
    -0.47
     entirety
    -0.47
    perty
    -0.47
    sharing
    -0.46
    VP
    -0.46
    POSITIVE LOGITS
     recommends
    0.81
     therefore
    0.78
     estimate
    0.67
     advises
    0.66
     conject
    0.64
     estimates
    0.64
     emphasizes
    0.62
     however
    0.62
     theor
    0.61
     calculates
    0.57
    Activations Density 1.369%

    No Known Activations