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. 11-RES-JB
    6. 2950
    Prev
    Next
    INDEX
    Explanations

    terms related to Jewish culture and communities

    oai_token-act-pair · gpt-3.5-turbo

    references to Jewish identity and community

    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
    aldo
    -0.73
    ttes
    -0.72
    Nap
    -0.71
    adoes
    -0.68
    doors
    -0.67
    mson
    -0.67
    )=(
    -0.66
    ugal
    -0.65
    aunder
    -0.64
    arget
    -0.63
    POSITIVE LOGITS
     Israelis
    0.97
     Sabbath
    0.97
     communal
    0.92
     Settlement
    0.86
     rabb
    0.86
     supremacist
    0.85
    inical
    0.85
     sett
    0.83
     settlers
    0.82
     Zionist
    0.82
    Activations Density 0.047%

    No Known Activations