© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    dates and places

    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
    +0.19
    0.9%
    481
    +0.12
    0.6%
    627
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.19
    0.03
    590
    +0.12
    0.03
    493
    +0.11
    0.03
    Negative Logits
     guiName
    -0.78
    conservancy
    -0.78
    etheless
    -0.76
    ecause
    -0.73
    %.
    -0.67
     ."
    -0.66
    discrimination
    -0.66
    wcs
    -0.63
    printf
    -0.60
    essel
    -0.59
    POSITIVE LOGITS
    ):
    1.62
    )
    1.55
    )/
    1.53
    )"
    1.50
    )]
    1.43
    )'
    1.43
    )|
    1.40
    )=
    1.35
    *)
    1.34
    )",
    1.32
    Activations Density 0.238%

    No Known Activations