© 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 1536
    9. 8-RES_FS1536-JB
    11. 1147
    Prev
    Next
    INDEX
    Explanations

    information regarding various news topics, including updates on people, economic expenses, engineering projects, scientific studies, and political reforms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    +0.63
    4.9%
    447
    +0.38
    3.0%
    87
    +0.24
    1.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.63
    0.15
    266
    +0.38
    0.43
    464
    +0.24
    0.21
    Negative Logits
    anwhile
    -0.54
    *.
    -0.50
    enegger
    -0.45
    _.
    -0.44
    !.
    -0.42
     respectively
    -0.42
     Vaugh
    -0.42
    +.
    -0.41
    ¢
    -0.40
    代
    -0.39
    POSITIVE LOGITS
     Rohingya
    0.36
     Allaah
    0.35
     OnePlus
    0.35
     Cannabis
    0.35
    ratom
    0.35
     Orioles
    0.34
     crochet
    0.34
     Guant
    0.34
     ICO
    0.33
     Naruto
    0.33
    Activations Density 17.109%

    No Known Activations