© 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 24576
    9. 8-RES_FS24576-JB
    11. 8849
    Prev
    Next
    INDEX
    Explanations

    phrases related to military aid and assistance to specific countries

    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
    447
    +0.17
    0.8%
    352
    +0.10
    0.5%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.17
    0.05
    288
    +0.10
    0.05
    51
    +0.10
    0.04
    Negative Logits
    ãĤ¦ãĤ¹
    -0.85
     ancest
    -0.70
    urities
    -0.69
    ierre
    -0.68
     Eater
    -0.67
    âĸ¬
    -0.65
    ãĥ´
    -0.64
    terness
    -0.63
     fry
    -0.63
    hma
    -0.62
    POSITIVE LOGITS
     aid
    1.05
     funding
    0.97
     funded
    0.96
     assistance
    0.96
     programmes
    0.95
     subsidies
    0.95
     reimburse
    0.95
     humanitarian
    0.93
     subsid
    0.93
     allocations
    0.93
    Activations Density 0.255%

    No Known Activations