© 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. 12697
    Prev
    Next
    INDEX
    Explanations

    descriptions of experiences and details related to family life

    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
    +0.47
    2.4%
    266
    +0.10
    0.5%
    372
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.47
    0.01
    266
    +0.10
    0.08
    45
    +0.09
    0.03
    Negative Logits
    eligible
    -0.73
     Certification
    -0.72
    Federal
    -0.71
    spons
    -0.69
     Provision
    -0.68
     expired
    -0.68
    ļéĨĴ
    -0.68
    heid
    -0.67
     abolished
    -0.66
     Welfare
    -0.66
    POSITIVE LOGITS
     cinematic
    1.18
     storytelling
    1.15
     realism
    1.09
     themes
    1.09
     juxtap
    1.08
     lyr
    1.04
     melanch
    1.04
     genre
    1.04
     visuals
    1.03
     tropes
    1.03
    Activations Density 1.035%

    No Known Activations