© 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. 7786
    Prev
    Next
    INDEX
    Explanations

    names of individuals, possibly related to sports or entertainment

    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
    742
    +0.15
    0.7%
    314
    +0.12
    0.6%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.15
    0.02
    627
    +0.12
    0.01
    102
    +0.11
    0.02
    Negative Logits
     reconcil
    -0.79
     appointments
    -0.78
     repay
    -0.77
     disapprove
    -0.73
     forgiven
    -0.71
     peripheral
    -0.71
     ¥
    -0.71
     reconcile
    -0.71
     occupancy
    -0.70
     textbooks
    -0.70
    POSITIVE LOGITS
    Fat
    1.17
    Spirit
    1.04
    Rust
    1.04
    Skip
    1.04
    Golden
    1.02
    Wild
    1.01
    Sem
    1.01
    Big
    1.00
    Hun
    1.00
    Rap
    1.00
    Activations Density 0.037%

    No Known Activations