© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4978
    Prev
    Next
    INDEX
    Explanations

    phrases related to Mormonism and LGBTQ rights

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to the Mormon Church and its related terminology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     MacArthur
    -0.67
    lihood
    -0.64
     Miranda
    -0.61
     MAD
    -0.58
     Fuk
    -0.56
     Nero
    -0.56
     Nvidia
    -0.55
     Joker
    -0.55
     Bayer
    -0.54
     tou
    -0.54
    POSITIVE LOGITS
    Leaks
    0.88
    ns
    0.85
     Jazz
    0.82
    CHAT
    0.80
     polygamy
    0.78
    Think
    0.77
    Policy
    0.77
    cius
    0.74
    Utah
    0.72
    ormon
    0.72
    Activations Density 0.047%

    No Known Activations