© 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 1536
    9. 8-RES_FS1536-JB
    11. 1096
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and creation of new buildings or institutions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    +0.17
    0.8%
    481
    +0.14
    0.6%
    459
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.17
    0.19
    288
    +0.14
    0.20
    459
    +0.12
    0.13
    Negative Logits
     Errors
    -0.72
    inventoryQuantity
    -0.70
     lows
    -0.63
     spilled
    -0.62
     wounds
    -0.61
     accidents
    -0.60
     corners
    -0.60
     Parenthood
    -0.60
     pauses
    -0.59
     extremes
    -0.58
    POSITIVE LOGITS
     capable
    0.98
     suitable
    0.97
     consisting
    0.92
     modeled
    0.91
     incorporating
    0.86
     dedicated
    0.85
     resembling
    0.82
     specializing
    0.81
     someday
    0.81
     embod
    0.81
    Activations Density 5.290%

    No Known Activations