© 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 12288
    9. 8-RES_FS12288-JB
    11. 10812
    Prev
    Next
    INDEX
    Explanations

    measurements related to height

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    762
    +0.11
    0.5%
    335
    +0.11
    0.5%
    99
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.11
    0.03
    222
    +0.11
    0.03
    238
    +0.11
    0.03
    Negative Logits
    eer
    -0.97
    icer
    -0.77
    actionDate
    -0.75
    udeb
    -0.74
    ãĤ±
    -0.72
    analysis
    -0.71
    enum
    -0.69
    eering
    -0.66
    YN
    -0.64
    eday
    -0.64
    POSITIVE LOGITS
     tall
    1.25
     diameter
    1.03
     elevation
    0.95
     taller
    0.94
     radius
    0.94
     ceilings
    0.93
     circumference
    0.88
    tall
    0.86
     lengths
    0.84
     wide
    0.83
    Activations Density 0.058%

    No Known Activations