© 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 49152
    9. 8-RES_FS49152-JB
    11. 45602
    Prev
    Next
    INDEX
    Explanations

    references to a specific brand of beer

    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
    447
    +0.15
    0.7%
    508
    +0.12
    0.5%
    761
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.15
    0.02
    761
    +0.12
    0.02
    659
    +0.11
    0.01
    Negative Logits
    liest
    -0.91
    ulatory
    -0.86
    ulates
    -0.85
    angular
    -0.84
     quo
    -0.83
    ulating
    -0.79
    rous
    -0.79
    ulator
    -0.75
    rely
    -0.74
    ulators
    -0.72
    POSITIVE LOGITS
     Miller
    0.85
     Mayhem
    0.81
     Lite
    0.80
    ophon
    0.75
    iday
    0.74
    quist
    0.74
    beer
    0.73
    myra
    0.71
    hound
    0.70
    burgh
    0.70
    Activations Density 0.007%

    No Known Activations