© 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. 41148
    Prev
    Next
    INDEX
    Explanations

    words related to specific sports statistics or player achievements

    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
    420
    +0.10
    0.4%
    59
    +0.09
    0.4%
    216
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.10
    0.01
    579
    +0.09
    0.01
    284
    +0.09
    0.01
    Negative Logits
    nesota
    -0.84
    abies
    -0.77
    ERAL
    -0.76
    INESS
    -0.76
    dfx
    -0.76
    perse
    -0.75
    olved
    -0.75
    neapolis
    -0.72
    tick
    -0.71
    omnia
    -0.70
    POSITIVE LOGITS
    zzi
    1.05
    ella
    0.89
    ño
    0.86
    zona
    0.81
    lli
    0.81
    astern
    0.79
    eli
    0.78
    tti
    0.74
    ktop
    0.74
    chnology
    0.73
    Activations Density 0.004%

    No Known Activations