© 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 1536
    9. 8-RES_FS1536-JB
    11. 1015
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    393
    +0.16
    0.7%
    362
    +0.13
    0.6%
    476
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.16
    669
    +0.13
    0.12
    611
    +0.10
    0.12
    Negative Logits
    Catalog
    -0.80
    igue
    -0.75
     istg
    -0.73
    /"
    -0.73
    .-
    -0.69
    Edge
    -0.67
    far
    -0.66
    forge
    -0.65
    .''.
    -0.64
    ](
    -0.64
    POSITIVE LOGITS
     these
    0.88
     those
    0.84
     mankind
    0.82
     humankind
    0.80
     each
    0.77
     our
    0.77
     course
    0.75
     the
    0.73
     sorts
    0.73
     oneself
    0.72
    Activations Density 1.968%

    No Known Activations