© 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. 16737
    Prev
    Next
    INDEX
    Explanations

    terms related to industries, markets, and business activities

    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
    724
    +0.12
    0.5%
    723
    +0.12
    0.5%
    606
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.04
    368
    +0.12
    0.04
    724
    +0.11
    0.04
    Negative Logits
     plaque
    -0.78
     omission
    -0.73
     apologise
    -0.69
    tein
    -0.69
     scrolls
    -0.68
     sentences
    -0.68
     cuff
    -0.66
     inscription
    -0.65
     delet
    -0.65
     deletion
    -0.64
    POSITIVE LOGITS
     dominated
    1.09
     booming
    1.07
     flourished
    1.07
     stagn
    0.96
     flourishing
    0.94
     thriving
    0.93
     rife
    0.91
     thri
    0.90
     evolving
    0.86
     stagnant
    0.86
    Activations Density 0.327%

    No Known Activations