© 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. 11921
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "bear" and related terms, including the football team, the animal, and figurative uses

    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
    52
    +0.11
    0.5%
    528
    +0.10
    0.5%
    246
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.11
    0.02
    366
    +0.10
    0.01
    66
    +0.10
    0.02
    Negative Logits
    istry
    -0.77
    lectic
    -0.73
    ADRA
    -0.72
    selves
    -0.70
     Gutenberg
    -0.68
    opus
    -0.67
    ablishment
    -0.66
    ubuntu
    -0.65
    isters
    -0.65
    arters
    -0.65
    POSITIVE LOGITS
     cub
    0.97
    bear
    0.90
     Bears
    0.87
     hug
    0.87
    xual
    0.84
     Grizz
    0.81
     hugs
    0.78
    beit
    0.78
     claws
    0.77
    cats
    0.74
    Activations Density 0.029%

    No Known Activations