© 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 24576
    9. 8-RES_FS24576-JB
    11. 14319
    Prev
    Next
    INDEX
    Explanations

    quantitative changes and trends in data

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    0.8%
    592
    +0.10
    0.5%
    274
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.16
    0.04
    559
    +0.10
    0.03
    368
    +0.09
    0.04
    Negative Logits
    tta
    -0.78
    sol
    -0.73
    ãĥīãĥ©
    -0.70
    eatured
    -0.68
    minecraft
    -0.67
     sar
    -0.66
    psc
    -0.65
    search
    -0.64
    verse
    -0.64
    finished
    -0.64
    POSITIVE LOGITS
     dramatically
    1.20
     markedly
    1.14
     sharply
    1.14
     exponentially
    1.13
     steadily
    1.10
     considerably
    1.08
     substantially
    1.07
     drastically
    1.01
     significantly
    1.00
     accordingly
    0.97
    Activations Density 0.094%

    No Known Activations