Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19015
    Prev
    Next
    INDEX
    Explanations

    statements related to international relations and political actions

    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
    385
    +0.10
    0.5%
    226
    +0.09
    0.4%
    758
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.10
    0.04
    665
    +0.09
    0.05
    385
    +0.08
    0.05
    Negative Logits
     upd
    -0.71
     Alto
    -0.69
     pandemonium
    -0.69
     Juven
    -0.65
     Bronx
    -0.65
    wordpress
    -0.64
     PCs
    -0.63
    fill
    -0.62
     epile
    -0.62
     Yose
    -0.62
    POSITIVE LOGITS
     NATO
    1.13
     Nato
    1.10
     allies
    1.00
     embassy
    0.99
     diplomatic
    0.97
     superpower
    0.93
     abroad
    0.92
     Allies
    0.92
     diplomats
    0.91
     embassies
    0.91
    Activations Density 0.469%

    No Known Activations