© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 789
    Prev
    Next
    INDEX
    Explanations

    facts or data related to economic and political aspects of China

    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
    314
    +0.10
    0.5%
    136
    +0.10
    0.5%
    466
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.10
    0.02
    25
    +0.10
    0.04
    611
    +0.09
    0.04
    Negative Logits
    angelo
    -0.72
     clos
    -0.71
    patch
    -0.71
     reperto
    -0.70
     lapt
    -0.70
    itiveness
    -0.66
    peer
    -0.65
    wcs
    -0.65
    oven
    -0.65
    bath
    -0.64
    POSITIVE LOGITS
     Liberia
    0.95
     Ireland
    0.93
     Macedonia
    0.93
     Yugoslavia
    0.92
     Latvia
    0.90
     Ghana
    0.90
     Cyprus
    0.89
     Finland
    0.87
    uador
    0.87
     Qatar
    0.87
    Activations Density 0.174%

    No Known Activations