© 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. 1449
    Prev
    Next
    INDEX
    Explanations

    references to changes or events happening over the past few days

    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
    430
    +0.10
    0.4%
    68
    +0.09
    0.4%
    589
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.05
    689
    +0.09
    0.04
    55
    +0.09
    0.04
    Negative Logits
     someday
    -0.82
     Benefits
    -0.65
    inav
    -0.65
     ut
    -0.63
    inse
    -0.61
     Type
    -0.61
     Codes
    -0.60
    insured
    -0.60
    reat
    -0.60
    inet
    -0.59
    POSITIVE LOGITS
    hift
    0.79
     afternoon
    0.78
    flower
    0.75
    ²¾
    0.73
    ı
    0.73
    imester
    0.72
    ebin
    0.72
     embold
    0.71
     Hannity
    0.71
     uproar
    0.70
    Activations Density 0.112%

    No Known Activations