© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21739
    Prev
    Next
    INDEX
    Explanations

    Japanese names, particularly those related to specific individuals like "Nakagami" and "Satoshi Nakamoto."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with a connection to Japanese pop culture or industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neut
    -0.75
     opener
    -0.72
     upkeep
    -0.67
     cheer
    -0.67
     prevailing
    -0.66
     sexes
    -0.64
     misc
    -0.63
     clos
    -0.62
     contraception
    -0.61
     fragmented
    -0.61
    POSITIVE LOGITS
    amoto
    1.92
    amura
    1.71
    azaki
    1.55
    asaki
    1.48
    urai
    1.30
    atsuki
    1.29
    akura
    1.26
    imura
    1.25
    anish
    1.25
    imoto
    1.21
    Activations Density 0.036%

    No Known Activations