© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41725
    Prev
    Next
    INDEX
    Explanations

    types of beer and beer-related terminology

    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
    481
    +0.17
    0.8%
    447
    +0.13
    0.6%
    459
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.17
    0.02
    76
    +0.13
    0.02
    634
    +0.10
    0.02
    Negative Logits
    MpServer
    -0.82
     Telecommunications
    -0.74
    operated
    -0.73
    iframe
    -0.73
    uchin
    -0.70
    abilia
    -0.70
    aido
    -0.69
    aldo
    -0.69
    chwitz
    -0.67
    andowski
    -0.67
    POSITIVE LOGITS
     brewed
    1.33
     brewer
    0.98
     tasting
    0.93
     IPA
    0.92
     flavored
    0.92
     flavor
    0.89
     brewing
    0.89
     brew
    0.88
     whiskey
    0.86
     tast
    0.86
    Activations Density 0.024%

    No Known Activations