© 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. 7883
    Prev
    Next
    INDEX
    Explanations

    references to "Law & Order" TV series

    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
    314
    +0.17
    0.8%
    384
    +0.11
    0.5%
    297
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.17
    0.03
    284
    +0.11
    0.04
    398
    +0.11
    0.03
    Negative Logits
    auga
    -0.85
    hiba
    -0.69
    earable
    -0.68
     crabs
    -0.64
    yip
    -0.63
    BIL
    -0.63
     Sunder
    -0.63
    hesda
    -0.61
    iliary
    -0.60
    href
    -0.60
    POSITIVE LOGITS
    enforcement
    1.00
    riage
    0.86
    abiding
    0.82
    rency
    0.77
     racket
    0.75
     jurisdiction
    0.75
    azeera
    0.73
    Runtime
    0.68
    clinton
    0.68
    ãĤ·ãĥ£
    0.67
    Activations Density 0.172%

    No Known Activations