© 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. 26709
    Prev
    Next
    INDEX
    Explanations

    names of prominent individuals in the entertainment industry

    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
    447
    +0.16
    0.7%
    481
    +0.15
    0.7%
    525
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    525
    +0.16
    0.05
    502
    +0.15
    0.05
    659
    +0.13
    0.05
    Negative Logits
    etheless
    -0.90
    oard
    -0.76
    apter
    -0.72
    âĸ¬
    -0.71
    Tar
    -0.69
     Pruitt
    -0.68
    Els
    -0.68
    intendent
    -0.67
    »Ĵ
    -0.66
    orage
    -0.65
    POSITIVE LOGITS
     Presents
    0.96
     fame
    0.84
     famously
    0.84
     Jr
    0.81
     Productions
    0.81
     III
    0.80
     QC
    0.79
     aka
    0.78
    enegger
    0.78
     movies
    0.74
    Activations Density 0.139%

    No Known Activations