© 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. 45694
    Prev
    Next
    INDEX
    Explanations

    statistical performance metrics in sports contexts

    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
    188
    +0.13
    0.6%
    497
    +0.09
    0.4%
    761
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.13
    0.02
    668
    +0.09
    0.02
    225
    +0.09
    0.02
    Negative Logits
     recess
    -0.70
    IRC
    -0.66
    ocrates
    -0.65
    izoph
    -0.64
    kat
    -0.64
     marsh
    -0.63
    mun
    -0.63
     Contents
    -0.62
     conting
    -0.61
    Chair
    -0.61
    POSITIVE LOGITS
     (.
    1.08
     offensively
    0.90
     fastball
    0.89
    BIP
    0.88
    verages
    0.82
     averaging
    0.81
     rating
    0.79
     Westbrook
    0.78
     athlet
    0.76
     ERA
    0.75
    Activations Density 0.044%

    No Known Activations