© 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 12288
    9. 8-RES_FS12288-JB
    11. 1214
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terminology related to surgery and physical conditions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    753
    +0.11
    0.5%
    8
    +0.10
    0.5%
    483
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    483
    +0.11
    0.03
    8
    +0.10
    0.03
    231
    +0.10
    0.03
    Negative Logits
    gate
    -0.76
    omin
    -0.73
    division
    -0.72
    omination
    -0.71
    pit
    -0.71
    agg
    -0.71
    76561
    -0.70
    ËĪ
    -0.68
    layer
    -0.68
    oat
    -0.67
    POSITIVE LOGITS
     fortunately
    0.90
    terday
    0.87
     luckily
    0.80
    adays
    0.79
     enough
    0.71
     thankfully
    0.69
    udeau
    0.68
     HuffPost
    0.68
    nown
    0.67
     someday
    0.65
    Activations Density 0.090%

    No Known Activations