© 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. 0-RES-JB
    11. 14989
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to religious figures or organizations, especially those related to the Jewish faith

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Rabb" or variations of "rabbi"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vm
    -0.78
    enance
    -0.69
     Vale
    -0.67
    src
    -0.66
    peak
    -0.63
    WP
    -0.63
     invade
    -0.61
    CS
    -0.61
     resource
    -0.60
    Variable
    -0.58
    POSITIVE LOGITS
     Rabb
    4.49
     rabb
    2.73
     Rabbi
    1.73
     rabbi
    1.72
     Judaism
    1.54
     Torah
    1.40
     synagogue
    1.31
    osher
    1.30
     Sabb
    1.25
    Jews
    1.25
    Activations Density 0.022%

    No Known Activations