© 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. 1830
    Prev
    Next
    INDEX
    Explanations

    mentions of names of political figures and their related activities

    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
    362
    +0.19
    0.9%
    608
    +0.17
    0.8%
    393
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.11
    608
    +0.17
    0.10
    385
    +0.16
    0.07
    Negative Logits
    elaide
    -0.77
    strate
    -0.74
    hops
    -0.74
     namely
    -0.73
    NB
    -0.73
    ère
    -0.72
    mares
    -0.70
    arate
    -0.70
    meric
    -0.69
    replace
    -0.69
    POSITIVE LOGITS
     notion
    1.45
     idea
    1.41
     possibility
    1.21
     outcome
    1.16
     latter
    1.13
     entirety
    1.09
     portrayal
    1.05
     plight
    1.04
     latest
    1.03
     slightest
    1.02
    Activations Density 0.404%

    No Known Activations