© 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. 45555
    Prev
    Next
    INDEX
    Explanations

    references to academic citations and authors in research studies

    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
    615
    +0.10
    0.5%
    329
    +0.09
    0.4%
    525
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.10
    0.01
    368
    +0.09
    0.01
    525
    +0.09
    0.01
    Negative Logits
     comprom
    -0.77
    FactoryReloaded
    -0.73
    adobe
    -0.63
    buster
    -0.63
     Username
    -0.63
     Maker
    -0.62
     breaker
    -0.60
     divest
    -0.60
    CLASS
    -0.59
     USPS
    -0.59
    POSITIVE LOGITS
    .,
    1.50
    .:
    1.02
    .;
    1.01
    .,"
    0.95
    .),
    0.95
    .).
    0.93
    orporated
    0.92
    inks
    0.89
    .):
    0.89
    ogue
    0.89
    Activations Density 0.004%

    No Known Activations