© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 41647
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts

    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
    393
    +0.17
    0.8%
    362
    +0.11
    0.5%
    476
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.05
    608
    +0.11
    0.05
    385
    +0.11
    0.04
    Negative Logits
    opsis
    -0.78
    feld
    -0.71
    ãĥ¡
    -0.71
    ected
    -0.71
    deals
    -0.70
    thood
    -0.69
    VERTISEMENT
    -0.66
    bourg
    -0.66
    worn
    -0.66
    iam
    -0.66
    POSITIVE LOGITS
     extent
    1.05
     electorate
    1.05
     Senate
    0.90
     legislature
    0.88
     senate
    0.88
     respective
    0.88
     nation
    0.87
     contrary
    0.86
     electors
    0.86
     heavens
    0.85
    Activations Density 0.112%

    No Known Activations