© 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. 0-RES-JB
    11. 1952
    Prev
    Next
    INDEX
    Explanations

    terms related to "Scientology."

    oai_token-act-pair · gpt-3.5-turbo

    references to Scientology

    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
    vas
    -0.80
     futures
    -0.71
     baskets
    -0.70
     barrel
    -0.70
     Iz
    -0.70
     dra
    -0.70
     fram
    -0.68
     RX
    -0.67
    Road
    -0.67
     collisions
    -0.66
    POSITIVE LOGITS
     Scientology
    4.18
     Scient
    2.78
     Hubbard
    1.89
     scient
    1.84
     Mormonism
    1.68
    Scient
    1.48
     Dian
    1.34
     Buddhism
    1.29
     Catholicism
    1.23
     Manson
    1.22
    Activations Density 0.037%

    No Known Activations