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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21663
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Korea

    oai_token-act-pair · gpt-3.5-turbo

    references to Korea and Korean-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mayweather
    -0.80
    llo
    -0.79
    MENTS
    -0.77
    ments
    -0.76
    MENT
    -0.75
    igue
    -0.72
    lli
    -0.71
    yard
    -0.71
    vol
    -0.70
    alg
    -0.69
    POSITIVE LOGITS
     peninsula
    1.05
    orea
    0.99
     Korea
    0.96
     Peninsula
    0.90
     ë
    0.85
     ì
    0.83
     Koreans
    0.81
     Jong
    0.78
     Sung
    0.78
     Pyongyang
    0.78
    Activations Density 0.023%

    No Known Activations