© 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 49152
    9. 8-RES_FS49152-JB
    11. 42848
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "stand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    314
    +0.11
    0.5%
    359
    +0.10
    0.5%
    274
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.11
    0.01
    274
    +0.10
    0.01
    676
    +0.10
    0.02
    Negative Logits
    EStream
    -0.84
    EStreamFrame
    -0.81
    actionDate
    -0.79
    cffff
    -0.77
    displayText
    -0.72
    REDACTED
    -0.70
    oleon
    -0.68
    tnc
    -0.68
     Intake
    -0.67
    sbm
    -0.65
    POSITIVE LOGITS
    still
    1.34
    bys
    1.11
    ings
    1.00
    alone
    1.00
    outs
    0.95
    pipe
    0.95
    ups
    0.95
    up
    0.94
    overs
    0.90
    offs
    0.90
    Activations Density 0.010%

    No Known Activations