© 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. 12259
    Prev
    Next
    INDEX
    Explanations

    years mentioned in the text

    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
    373
    +0.13
    0.6%
    130
    +0.10
    0.5%
    462
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.13
    0.04
    130
    +0.10
    0.04
    463
    +0.09
    0.04
    Negative Logits
    achus
    -0.69
    chat
    -0.65
    HUD
    -0.64
     subp
    -0.64
     akin
    -0.61
    chy
    -0.61
    peak
    -0.61
    Apps
    -0.58
    illions
    -0.57
    perse
    -0.57
    POSITIVE LOGITS
     olds
    0.90
     old
    0.89
    old
    0.87
     anniversary
    0.83
     ago
    0.79
    olds
    0.78
    OLD
    0.69
     Ago
    0.68
     veteran
    0.68
     Anniversary
    0.67
    Activations Density 0.031%

    No Known Activations