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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 24326
    Prev
    Next
    INDEX
    Explanations

    terms related to Korea or Korean entities

    oai_token-act-pair · gpt-3.5-turbo

    references to Korea and Korean-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENTS
    -0.82
    yard
    -0.78
    MENT
    -0.77
    llo
    -0.76
     Mayweather
    -0.74
    ashtra
    -0.73
    ments
    -0.72
    igue
    -0.70
    ault
    -0.68
    eus
    -0.68
    POSITIVE LOGITS
     peninsula
    1.09
    orea
    1.09
     Peninsula
    0.96
     Korea
    0.95
     ë
    0.90
     ì
    0.89
     Sung
    0.87
    ongyang
    0.86
    ë
    0.84
     Jong
    0.83
    Activations Density 0.029%

    No Known Activations