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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4495
    Prev
    Next
    INDEX
    Explanations

    terms related to Hong Kong

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Hong Kong

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ally
    -0.75
    nesota
    -0.71
    unct
    -0.69
     placeholder
    -0.65
    igm
    -0.65
    kick
    -0.64
    selection
    -0.63
     ticks
    -0.63
     Archdemon
    -0.63
    uality
    -0.61
    POSITIVE LOGITS
     Kong
    1.45
    awei
    1.22
     Hong
    1.03
    Hong
    1.00
    zhou
    0.87
    nam
    0.86
     Hua
    0.85
     Dong
    0.85
    wei
    0.84
    moon
    0.84
    Activations Density 0.006%

    No Known Activations