© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19686
    Prev
    Next
    INDEX
    Explanations

    scientific studies and research related to health, diet, and medical conditions

    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
    724
    +0.10
    0.5%
    472
    +0.10
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.10
    0.03
    679
    +0.10
    0.04
    724
    +0.10
    0.03
    Negative Logits
    gur
    -0.69
    riot
    -0.66
    css
    -0.66
     possessions
    -0.64
     Petty
    -0.64
    atra
    -0.64
     Rapids
    -0.63
     Staples
    -0.62
     Randolph
    -0.62
     granite
    -0.62
    POSITIVE LOGITS
     involving
    1.00
     conducted
    0.98
     studies
    0.97
     evaluating
    0.93
     examining
    0.92
     published
    0.90
    Study
    0.89
     hypothes
    0.89
     investigating
    0.87
    Reviewed
    0.87
    Activations Density 0.104%

    No Known Activations