© 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. 11-RES-JB
    11. 18820
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or events, particularly relating to Chinese media or politics

    oai_token-act-pair · gpt-3.5-turbo

    significant events or reports related to China

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Plugin
    -1.00
     Ajax
    -0.95
     Bucks
    -0.93
    iott
    -0.91
    reth
    -0.86
     Hitchcock
    -0.85
    Philadelphia
    -0.84
     Brees
    -0.83
     Amanda
    -0.83
     Omaha
    -0.83
    POSITIVE LOGITS
     Beijing
    2.46
     Chinese
    2.38
     Shanghai
    2.36
     China
    2.28
     Guang
    2.24
     Xi
    2.24
    Chinese
    2.22
     yuan
    2.19
    China
    2.15
     Xin
    2.13
    Activations Density 1.088%

    No Known Activations