© 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 24576
    9. 8-RES_FS24576-JB
    11. 7942
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Betz"

    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
    +0.11
    0.5%
    659
    +0.10
    0.5%
    669
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.04
    284
    +0.10
    0.03
    700
    +0.09
    0.03
    Negative Logits
     ransom
    -0.68
     Scots
    -0.67
    naissance
    -0.62
     behavi
    -0.62
     Columb
    -0.61
     foss
    -0.59
    ndra
    -0.58
     frust
    -0.57
     foremost
    -0.57
     Latin
    -0.57
    POSITIVE LOGITS
    ombie
    1.55
    ombies
    1.29
    enegger
    1.20
    gerald
    1.08
    hao
    1.08
    ymes
    1.08
    alez
    1.05
    ewski
    1.04
    arella
    1.02
    ebra
    1.01
    Activations Density 0.043%

    No Known Activations