© 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. 14047
    Prev
    Next
    INDEX
    Explanations

    descriptions of colors or physical attributes

    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
    459
    +0.13
    0.6%
    290
    +0.09
    0.4%
    315
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.13
    0.04
    289
    +0.09
    0.02
    251
    +0.08
    0.04
    Negative Logits
    =-=-=-=-
    -0.96
    ========
    -0.81
    Init
    -0.77
    Players
    -0.76
    arenthood
    -0.73
    HAM
    -0.73
    Recent
    -0.72
    OPA
    -0.71
    olkien
    -0.71
    Corp
    -0.70
    POSITIVE LOGITS
     tint
    1.16
     coloured
    1.15
     colored
    1.14
     striped
    1.10
     stripe
    1.08
     hue
    1.07
     glow
    1.07
     dye
    1.06
     ribbon
    1.04
     marble
    1.02
    Activations Density 0.080%

    No Known Activations