© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10072
    Prev
    Next
    INDEX
    Explanations

    references to the country Taiwan

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Taiwan or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anchester
    -0.71
    entials
    -0.67
    lihood
    -0.64
    ãĥı
    -0.63
     pumps
    -0.63
     à¤
    -0.62
     Pryor
    -0.62
    ONSORED
    -0.62
    icka
    -0.62
    baugh
    -0.62
    POSITIVE LOGITS
    pei
    1.69
    yang
    0.99
     Strait
    0.99
     Chi
    0.96
     Tai
    0.95
    Tai
    0.89
     Xuan
    0.85
     Dai
    0.85
    wan
    0.84
     Taiwanese
    0.83
    Activations Density 0.020%

    No Known Activations