© 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 49152
    9. 8-RES_FS49152-JB
    11. 41131
    Prev
    Next
    INDEX
    Explanations

    references to adaptations of stories and source materials for films or series

    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
    286
    +0.13
    0.6%
    296
    +0.13
    0.6%
    235
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.13
    0.02
    296
    +0.13
    0.02
    362
    +0.12
    0.02
    Negative Logits
    acity
    -0.88
    gencies
    -0.86
    alde
    -0.82
    ffect
    -0.79
    isphere
    -0.79
    inence
    -0.77
    teness
    -0.77
    ctic
    -0.77
    apo
    -0.75
    wcs
    -0.74
    POSITIVE LOGITS
     bestselling
    0.85
     screenplay
    0.84
     memoir
    0.77
     Artemis
    0.76
     loosely
    0.75
     novels
    0.75
     autobiography
    0.74
     Akira
    0.73
     novel
    0.72
     acclaimed
    0.71
    Activations Density 0.045%

    No Known Activations