© 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. 11-RES-JB
    11. 3513
    Prev
    Next
    INDEX
    Explanations

    adjectives related to different nationalities or cultural cuisines

    oai_token-act-pair · gpt-3.5-turbo

    references to various national cuisines or ethnic food types

    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
    inson
    -0.77
    abilities
    -0.76
    ueller
    -0.73
    isconsin
    -0.72
     sustained
    -0.71
    igham
    -0.70
    gb
    -0.69
    */(
    -0.69
    tracking
    -0.69
    here
    -0.69
    POSITIVE LOGITS
     proverb
    1.07
    apolis
    0.98
     cuisine
    0.94
    istani
    0.91
     immigrant
    0.86
    oslov
    0.86
     Style
    0.85
     Rite
    0.84
     shepherd
    0.84
     slang
    0.83
    Activations Density 0.153%

    No Known Activations