© 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. 5143
    Prev
    Next
    INDEX
    Explanations

    research articles on ethnic conflict and civil war

    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
    373
    +0.13
    0.6%
    713
    +0.10
    0.5%
    297
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.13
    0.03
    126
    +0.10
    0.03
    232
    +0.10
    0.03
    Negative Logits
    {"
    -0.71
    Ore
    -0.68
     quir
    -0.67
     eater
    -0.64
     watering
    -0.63
    atel
    -0.62
    auder
    -0.61
    gallery
    -0.60
    depending
    -0.60
    ŀ
    -0.60
    POSITIVE LOGITS
     Strategies
    1.20
     Perspect
    1.13
     Concepts
    1.04
     Handbook
    1.03
     Learned
    1.02
     Patterns
    1.00
     Lessons
    0.99
     Strategy
    0.98
     Concept
    0.97
     Politics
    0.96
    Activations Density 0.257%

    No Known Activations