© 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. 19715
    Prev
    Next
    INDEX
    Explanations

    terms related to political independence

    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
    288
    +0.16
    0.7%
    263
    +0.14
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.16
    0.02
    288
    +0.14
    0.02
    673
    +0.12
    0.02
    Negative Logits
    bilt
    -0.87
    enegger
    -0.83
    geon
    -0.75
    geries
    -0.74
    ergy
    -0.74
    ning
    -0.70
    tail
    -0.69
    eor
    -0.69
    mers
    -0.67
    ãĥ¥
    -0.66
    POSITIVE LOGITS
     referendum
    1.06
     oath
    0.81
     Catalonia
    0.76
     independence
    0.75
    yip
    0.74
     coff
    0.69
    arta
    0.67
    inally
    0.67
     Latvia
    0.67
    eas
    0.67
    Activations Density 0.025%

    No Known Activations