© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22328
    Prev
    Next
    INDEX
    Explanations

    mentions of Chinese-related entities or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to "Chinese" as a subject or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffer
    -0.74
     Amend
    -0.69
    Alert
    -0.67
     Osw
    -0.67
     Rutherford
    -0.65
    odder
    -0.64
    Monitor
    -0.64
    omnia
    -0.64
    iott
    -0.64
     Payton
    -0.63
    POSITIVE LOGITS
     Chinese
    3.64
    Chinese
    3.41
     Taiwanese
    2.68
     China
    2.48
    China
    2.36
     Vietnamese
    2.31
     Japanese
    2.25
     Mandarin
    2.24
     Beijing
    2.20
     Tibetan
    2.19
    Activations Density 0.022%

    No Known Activations