© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 45437
    Prev
    Next
    INDEX
    Explanations

    concepts related to the longevity and lifespan of objects or entities

    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
    724
    +0.12
    0.6%
    762
    +0.12
    0.5%
    46
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.12
    0.02
    132
    +0.12
    0.02
    439
    +0.10
    0.01
    Negative Logits
    anooga
    -0.82
    ij士
    -0.80
    Ń·
    -0.80
    unin
    -0.72
     glim
    -0.70
    riad
    -0.70
    äºĶ
    -0.69
    ãĤ¢ãĥ«
    -0.68
    kie
    -0.66
     Guilty
    -0.65
    POSITIVE LOGITS
     expectancy
    1.32
    cation
    0.97
     span
    0.95
    ecycle
    0.93
    span
    0.92
    boats
    0.90
    cycle
    0.86
    lasting
    0.86
    cycles
    0.85
    frames
    0.84
    Activations Density 0.020%

    No Known Activations