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

    Neuronpedia

    Jacobian LensNEW
    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. 11035
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of countries, leaders, and organizations

    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
    362
    +0.14
    0.6%
    154
    +0.10
    0.5%
    693
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.06
    616
    +0.10
    0.05
    693
    +0.10
    0.05
    Negative Logits
    ording
    -0.81
    table
    -0.79
    lished
    -0.77
    Guest
    -0.76
    athon
    -0.76
    trace
    -0.76
    Tickets
    -0.73
    event
    -0.73
     Bunny
    -0.73
    Denver
    -0.72
    POSITIVE LOGITS
     sovereignty
    1.18
     own
    1.13
     diplomats
    1.11
     territorial
    1.10
     nationals
    1.10
     annexation
    1.07
     sovereign
    1.07
     neighbours
    1.05
     allies
    1.02
     diplomatic
    1.02
    Activations Density 0.178%

    No Known Activations