© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 17118
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Uzbekistan

    oai_token-act-pair · gpt-3.5-turbo

    references to Uzbekistan and its relationship with India and other countries

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ppard
    -0.72
    ODUCT
    -0.67
    Values
    -0.65
    advertisement
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
     Ange
    -0.64
     Gutenberg
    -0.64
    essler
    -0.64
    Planet
    -0.63
    enment
    -0.63
    POSITIVE LOGITS
    istani
    1.24
    istan
    1.19
     citiz
    1.02
     Uzbek
    0.99
    stan
    0.98
    zbek
    0.95
    oslov
    0.91
    oglu
    0.90
    wana
    0.88
     Kul
    0.85
    Activations Density 0.013%

    No Known Activations