© 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. 41513
    Prev
    Next
    INDEX
    Explanations

    the act of gathering or accumulating items or data

    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
    314
    +0.13
    0.6%
    71
    +0.10
    0.5%
    677
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.13
    0.02
    26
    +0.10
    0.02
    570
    +0.10
    0.01
    Negative Logits
    forth
    -0.81
    witz
    -0.73
    ellen
    -0.72
    pher
    -0.69
    ned
    -0.68
    ffe
    -0.64
     coasts
    -0.63
     submer
    -0.62
     Kardashian
    -0.61
     understands
    -0.58
    POSITIVE LOGITS
     signatures
    1.03
     royalties
    0.87
    ively
    0.83
    ivist
    0.81
    ennial
    0.81
    ibles
    0.79
     dues
    0.77
    ertation
    0.76
    ographs
    0.75
     donations
    0.75
    Activations Density 0.017%

    No Known Activations