Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 19109
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Kosher"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kos" and related terms or concepts, particularly in the context of kosher food and community

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.89
    osterone
    -0.78
    skirts
    -0.71
     Highlander
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.67
     Lauder
    -0.65
     Oaks
    -0.65
     Reggie
    -0.64
    OWS
    -0.62
    ISM
    -0.62
    POSITIVE LOGITS
    idon
    1.15
    cius
    1.02
    ket
    1.02
     Kos
    1.01
    lyak
    0.97
    kie
    0.96
    nown
    0.95
    utz
    0.95
    ovan
    0.95
    ugi
    0.92
    Activations Density 0.008%

    No Known Activations