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. 11-RES-JB
    6. 8542
    Prev
    Next
    INDEX
    Explanations

    information related to political events and organizations in South Korea, particularly in Seoul

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and dates in a news context

    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
    aukee
    -1.01
     Manit
    -0.98
     Parm
    -0.95
     Vermont
    -0.92
     barn
    -0.91
     Quebec
    -0.89
     Arkham
    -0.84
     basil
    -0.83
     ric
    -0.83
    Ott
    -0.83
    POSITIVE LOGITS
     Seoul
    2.15
     Choi
    2.10
     Koreans
    2.10
     Korea
    2.09
     Korean
    2.08
     Cheong
    1.88
     ì
    1.83
     Kang
    1.72
    ì
    1.72
    ê
    1.72
    Activations Density 0.408%

    No Known Activations