© 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. 4721
    Prev
    Next
    INDEX
    Explanations

    proper nouns of names of people, locations, and organizations

    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
    393
    +0.17
    0.8%
    362
    +0.16
    0.7%
    745
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.07
    385
    +0.16
    0.05
    393
    +0.12
    0.05
    Negative Logits
    rix
    -0.85
    eness
    -0.75
    fy
    -0.70
     alone
    -0.69
    lance
    -0.68
    fully
    -0.68
    aml
    -0.67
     anew
    -0.67
     wisely
    -0.67
    ontent
    -0.67
    POSITIVE LOGITS
     entrance
    1.22
     entrances
    1.08
     aforementioned
    1.04
     nearest
    1.04
     Statue
    1.01
     city
    0.99
     main
    0.99
     gates
    0.99
     courthouse
    0.96
     intersection
    0.95
    Activations Density 0.197%

    No Known Activations