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. 10-RES-JB
    6. 17677
    Prev
    Next
    INDEX
    Explanations

    locations and names with Japanese origin

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and governmental responsibilities in Japan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uliffe
    -0.96
     BLM
    -0.85
     Lyons
    -0.84
    ̶
    -0.83
     Philly
    -0.82
     Bray
    -0.81
    Colorado
    -0.80
     Dixon
    -0.77
     Malone
    -0.76
    espie
    -0.76
    POSITIVE LOGITS
    Japanese
    1.91
     Osaka
    1.90
    Japan
    1.88
     Japanese
    1.87
     Japan
    1.86
     Tokyo
    1.86
     Kyoto
    1.81
    Tok
    1.80
     Hiro
    1.75
     Fuji
    1.75
    Activations Density 0.721%

    No Known Activations