© 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 49152
    9. 8-RES_FS49152-JB
    11. 26589
    Prev
    Next
    INDEX
    Explanations

    references to the United Kingdom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.14
    0.6%
    329
    +0.10
    0.4%
    493
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.14
    0.01
    97
    +0.10
    0.01
    67
    +0.09
    0.01
    Negative Logits
    ovie
    -0.82
    emy
    -0.77
    ADRA
    -0.69
    ymes
    -0.68
    regor
    -0.65
    helle
    -0.65
    BOOK
    -0.65
    sense
    -0.64
    iosity
    -0.64
    ²¾
    -0.64
    POSITIVE LOGITS
     Parliament
    0.91
     Columbia
    0.87
     Columb
    0.87
     Independence
    0.84
     Sabha
    0.80
     Geological
    0.79
     Embassy
    0.78
     Aerospace
    0.78
     Broadcasting
    0.78
     Isles
    0.77
    Activations Density 0.013%

    No Known Activations