© 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. 24077
    Prev
    Next
    INDEX
    Explanations

    the definite article "the."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    393
    +0.17
    0.8%
    362
    +0.16
    0.7%
    481
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.07
    393
    +0.16
    0.05
    608
    +0.14
    0.06
    Negative Logits
     according
    -0.69
     suppose
    -0.65
    thood
    -0.64
    iffe
    -0.64
    JUST
    -0.64
    tackle
    -0.64
    tec
    -0.62
    âĸł
    -0.61
    âĿ
    -0.61
    wd
    -0.59
    POSITIVE LOGITS
     ensuing
    1.13
     resultant
    1.09
     rest
    1.07
     remainder
    1.04
     resulting
    1.02
     accompanying
    0.99
     corresponding
    0.98
     wider
    0.98
     aforementioned
    0.98
     entirety
    0.95
    Activations Density 0.159%

    No Known Activations