© 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. 12166
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to materials, design, and evaluation

    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
    480
    +0.57
    3.1%
    266
    +0.14
    0.7%
    317
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.57
    0.02
    266
    +0.14
    0.10
    377
    +0.08
    0.09
    Negative Logits
     Gamble
    -0.56
     partying
    -0.55
    ibles
    -0.51
     Canaveral
    -0.51
     Activate
    -0.51
     stunts
    -0.51
    wives
    -0.49
     raining
    -0.49
    estate
    -0.49
     nightclub
    -0.49
    POSITIVE LOGITS
     reader
    1.08
     readers
    0.98
     conject
    0.85
     enlight
    0.84
     eluc
    0.84
     summarize
    0.83
     scholarly
    0.78
     reprint
    0.78
     summar
    0.78
     Readers
    0.78
    Activations Density 1.207%

    No Known Activations