© 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. 7709
    Prev
    Next
    INDEX
    Explanations

    terms related to various industries and specific contexts like food, automotive, hockey, politics, aviation, physics, and rugby

    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%
    132
    +0.09
    0.4%
    726
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.09
    575
    +0.09
    0.06
    132
    +0.09
    0.05
    Negative Logits
    raviolet
    -0.75
    ||||
    -0.72
    lain
    -0.72
     Naval
    -0.71
     AFB
    -0.71
    DAQ
    -0.65
    ushima
    -0.65
    /.
    -0.64
    âĵĺ
    -0.64
    ral
    -0.63
    POSITIVE LOGITS
     historian
    0.96
     historians
    0.88
     philos
    0.86
    week
    0.82
     landscape
    0.80
     jargon
    0.79
     analyst
    0.78
     insiders
    0.73
    odynam
    0.72
     consultant
    0.72
    Activations Density 0.399%

    No Known Activations