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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 15211
    Prev
    Next
    INDEX
    Explanations

    Japanese names and related terms

    oai_token-act-pair · gpt-3.5-turbo

    names of Japanese individuals or companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.80
     newsp
    -0.73
     Hallow
    -0.69
     Capitals
    -0.66
     Hitman
    -0.63
    sylv
    -0.62
     Bett
    -0.62
     clipboard
    -0.62
     Libertarian
    -0.61
     winners
    -0.61
    POSITIVE LOGITS
    ishi
    1.51
    utsu
    1.13
    uchi
    1.10
    ushima
    1.05
    oka
    1.00
    terness
    0.94
    imoto
    0.91
    imi
    0.88
    oga
    0.87
    ima
    0.87
    Activations Density 0.012%

    No Known Activations