© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3663
    Prev
    Next
    INDEX
    Explanations

    non-English words related to different languages and regions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    6
    +0.12
    0.6%
    50
    +0.12
    0.5%
    51
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.02
    284
    +0.12
    0.02
    50
    +0.12
    0.02
    Negative Logits
    cham
    -0.78
     narrowly
    -0.77
     challeng
    -0.75
     disadvant
    -0.74
     synerg
    -0.74
     wrinkles
    -0.74
    undai
    -0.74
     manif
    -0.73
     casinos
    -0.72
     breadth
    -0.72
    POSITIVE LOGITS
    ा
    1.59
    à¥
    1.51
    ר
    1.44
    à¤
    1.43
    ×Ļ×
    1.40
    ×ķ
    1.36
    ×Ķ
    1.30
    ׾
    1.28
    ×
    1.26
    ת
    1.24
    Activations Density 0.018%

    No Known Activations