© 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. 8737
    Prev
    Next
    INDEX
    Explanations

    keywords related to data analysis and statistical modeling, along with terms related to technology, software, and specific programming languages

    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
    84
    +0.12
    0.5%
    726
    +0.09
    0.4%
    238
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.12
    0.01
    332
    +0.09
    0.01
    326
    +0.09
    0.01
    Negative Logits
    ians
    -0.70
    shire
    -0.67
    ity
    -0.66
    rade
    -0.66
    BAT
    -0.66
    swer
    -0.65
    spot
    -0.65
    founded
    -0.63
    sit
    -0.62
    sed
    -0.62
    POSITIVE LOGITS
     slices
    1.11
     slice
    1.03
     bread
    0.83
    meal
    0.82
    anut
    0.77
     sliced
    0.75
     pies
    0.74
     slicing
    0.72
    eki
    0.71
    slice
    0.70
    Activations Density 0.030%

    No Known Activations