Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12631
    Prev
    Next
    INDEX
    Explanations

    specific locations or entities related to the region of Guangdong

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or provinces in a broader context

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

    No Comments

    Negative Logits
    oscope
    -0.86
    ocene
    -0.78
    atives
    -0.73
    izer
    -0.72
    rencies
    -0.72
    atively
    -0.72
    ativity
    -0.71
    ocaust
    -0.70
    apult
    -0.69
     replay
    -0.68
    POSITIVE LOGITS
    zhou
    1.03
    rir
    0.88
     Guang
    0.87
    shire
    0.78
     Qiao
    0.76
    ILA
    0.75
    iors
    0.75
    hou
    0.75
    ľ
    0.74
    ilipp
    0.74
    Activations Density 0.018%

    No Known Activations