© 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. 829
    Prev
    Next
    INDEX
    Explanations

    phrases related to international relationships, agreements, and tensions

    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
    764
    +0.10
    0.5%
    435
    +0.10
    0.4%
    385
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.10
    0.06
    385
    +0.10
    0.09
    79
    +0.09
    0.07
    Negative Logits
    emetery
    -0.94
     Died
    -0.80
     Bucc
    -0.78
    wordpress
    -0.75
     Darrell
    -0.75
     Loft
    -0.72
     ped
    -0.71
    Adult
    -0.71
     Vick
    -0.71
    Untitled
    -0.70
    POSITIVE LOGITS
     Nato
    1.40
     NATO
    1.39
     diplomatic
    1.32
     countries
    1.32
     WTO
    1.27
     superpower
    1.26
     treaty
    1.26
     treaties
    1.26
     Countries
    1.25
     bilateral
    1.25
    Activations Density 1.559%

    No Known Activations