© 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. 11834
    Prev
    Next
    INDEX
    Explanations

    statements expressing beliefs or opinions, especially optimism and confidence about future plans or developments

    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
    563
    +0.10
    0.5%
    507
    +0.10
    0.5%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.10
    0.05
    177
    +0.10
    0.04
    507
    +0.09
    0.04
    Negative Logits
     Himself
    -0.67
    upper
    -0.65
    RAW
    -0.65
    figure
    -0.61
    ãĥĺ
    -0.60
     Bundy
    -0.59
     lobe
    -0.58
     earthqu
    -0.58
     erupt
    -0.58
     me
    -0.57
    POSITIVE LOGITS
    phas
    0.88
     fostering
    0.77
    onen
    0.74
     strongly
    0.69
    hement
    0.69
     passionately
    0.68
     rigorous
    0.67
     offering
    0.66
    orously
    0.64
     incent
    0.64
    Activations Density 0.161%

    No Known Activations