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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 2775
    Prev
    Next
    INDEX
    Explanations

    mentions of or related to Japan and Japanese culture

    oai_token-act-pair · gpt-3.5-turbo

    references to Japanese culture or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lier
    -0.97
    rences
    -0.84
    lain
    -0.84
    mble
    -0.83
    rent
    -0.83
    vable
    -0.82
    ully
    -0.82
    aucus
    -0.81
    stre
    -0.80
    izons
    -0.80
    POSITIVE LOGITS
     Yen
    0.95
     nationals
    0.77
     Nadu
    0.76
     yen
    0.73
     ancestry
    0.73
     heritage
    0.73
     translation
    0.72
     Inquisition
    0.71
     lantern
    0.71
     speakers
    0.70
    Activations Density 0.029%

    No Known Activations