© 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. 10-RES-JB
    11. 3338
    Prev
    Next
    INDEX
    Explanations

    mentions of specific religious entities or organizations, particularly churches

    oai_token-act-pair · gpt-3.5-turbo

    references to various religious organizations, particularly those related to Christianity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.69
     veins
    -0.68
     deadlines
    -0.67
     centrif
    -0.66
     arsen
    -0.65
     iceberg
    -0.63
     bruises
    -0.63
    abus
    -0.63
    itu
    -0.62
    azeera
    -0.62
    POSITIVE LOGITS
     Latter
    1.15
     Jesus
    1.13
     Scientology
    1.12
     Christ
    1.03
     Savior
    0.96
     Messiah
    0.94
    Jesus
    0.92
     Healer
    0.91
     Satan
    0.90
     Sisters
    0.90
    Activations Density 0.051%

    No Known Activations