© 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 12288
    9. 8-RES_FS12288-JB
    11. 1513
    Prev
    Next
    INDEX
    Explanations

    linguistic patterns related to authority, governance, and control

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    67
    +0.13
    0.6%
    421
    +0.10
    0.5%
    269
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.13
    0.05
    505
    +0.10
    0.04
    507
    +0.10
    0.04
    Negative Logits
    ittal
    -0.82
     excuse
    -0.71
    eds
    -0.65
    ym
    -0.64
    Acknowled
    -0.63
    hon
    -0.63
    esides
    -0.63
    spot
    -0.61
    vil
    -0.60
    prone
    -0.60
    POSITIVE LOGITS
    orously
    0.86
     affairs
    0.80
    ulate
    0.78
    uate
    0.75
     them
    0.71
     everything
    0.70
    glers
    0.69
     airflow
    0.69
     traffic
    0.68
     our
    0.67
    Activations Density 0.277%

    No Known Activations