© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    unusual, dark, or notable visual elements

    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
    447
    +0.15
    0.7%
    481
    +0.14
    0.6%
    218
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.15
    0.05
    362
    +0.14
    0.04
    268
    +0.13
    0.02
    Negative Logits
    imester
    -0.92
    adan
    -0.78
     depended
    -0.74
    assisted
    -0.73
    inion
    -0.73
    rer
    -0.71
    ourt
    -0.71
    rates
    -0.70
    agonist
    -0.70
    independence
    -0.69
    POSITIVE LOGITS
     lifeless
    1.06
     glowing
    1.05
     faint
    1.05
     resemblance
    1.02
     gaping
    0.98
     strange
    0.95
     unmarked
    0.95
     flickering
    0.94
     charred
    0.94
     blurry
    0.93
    Activations Density 0.290%

    No Known Activations