© 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 EvalsExportsAPI 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. 8-RES-JB
    11. 986
    Prev
    Next
    INDEX
    Explanations

    terms related to the Church of Jesus Christ of Latter-day Saints

    oai_token-act-pair · gpt-3.5-turbo

    references to the Church of Jesus Christ of Latter-day Saints (Mormons)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -1.11
    Downloadha
    -0.83
    ahime
    -0.73
     tremend
    -0.72
    onz
    -0.72
    uner
    -0.66
    uca
    -0.65
    urized
    -0.64
    RED
    -0.64
    endo
    -0.63
    POSITIVE LOGITS
     Saints
    0.81
     Islands
    0.73
     Mub
    0.70
     Oaks
    0.70
     Saint
    0.69
    holders
    0.67
     Advent
    0.65
    backer
    0.64
     Presbyter
    0.63
     Order
    0.63
    Activations Density 0.074%

    No Known Activations