© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2200
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Japan

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Japan and related entities

    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
    riers
    -0.79
    rent
    -0.77
    vable
    -0.75
    staking
    -0.73
    Berry
    -0.72
     Haitian
    -0.70
    thereal
    -0.69
     BET
    -0.68
     Maher
    -0.68
    Denver
    -0.68
    POSITIVE LOGITS
     yen
    1.12
     Yen
    1.08
    imura
    1.06
    £ı
    1.00
    oka
    0.97
    iji
    0.95
    itsu
    0.88
     Mits
    0.88
    ikawa
    0.88
     Japan
    0.86
    Activations Density 0.045%

    No Known Activations