© 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 EvalsExportsAPI 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. 18111
    Prev
    Next
    INDEX
    Explanations

    hyphenated compound words

    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
    480
    +0.65
    4.3%
    87
    +0.27
    1.8%
    266
    +0.19
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.65
    0.12
    124
    +0.27
    0.09
    314
    +0.19
    0.03
    Negative Logits
     Norris
    -0.61
     Dickinson
    -0.55
     Rica
    -0.54
     Borders
    -0.52
    kson
    -0.50
     Arabian
    -0.50
     proport
    -0.47
     Debor
    -0.47
     caut
    -0.46
     susp
    -0.45
    POSITIVE LOGITS
    sized
    0.86
    based
    0.84
    themed
    0.83
    level
    0.79
    oriented
    0.76
    generation
    0.76
    derived
    0.75
    series
    0.75
    driven
    0.75
    backed
    0.74
    Activations Density 0.224%

    No Known Activations