© 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. 12641
    Prev
    Next
    INDEX
    Explanations

    mentions of people and events in a social setting, possibly from news articles or discussions

    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
    480
    +0.51
    4.2%
    87
    +0.35
    2.9%
    266
    +0.21
    1.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.51
    0.07
    266
    +0.35
    0.17
    87
    +0.21
    -0.06
    Negative Logits
    enegger
    -0.41
     disadvant
    -0.39
     destro
    -0.38
     helicop
    -0.36
    sic
    -0.35
     Seym
    -0.33
    jri
    -0.31
     nep
    -0.31
     behav
    -0.31
     hemor
    -0.31
    POSITIVE LOGITS
     âĢº
    0.33
    cipled
    0.32
     ):
    0.32
    Ĥİ
    0.32
    taboola
    0.30
     GeForce
    0.30
     Belfast
    0.29
    \":
    0.29
    ciples
    0.29
    º
    0.29
    Activations Density 2.836%

    No Known Activations