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. 0-RES-JB
    6. 21394
    Prev
    Next
    INDEX
    Explanations

    terms related to secularism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to secularism and its implications in society

    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
     Squad
    -0.77
     Yards
    -0.75
     Leaf
    -0.73
    zilla
    -0.71
    apper
    -0.70
     Rhino
    -0.70
    breaker
    -0.69
     RTX
    -0.69
     Pokémon
    -0.69
     Bounty
    -0.68
    POSITIVE LOGITS
     secular
    3.65
     atheist
    1.94
     atheism
    1.80
     atheists
    1.78
     religious
    1.62
     relig
    1.62
    religious
    1.53
     theological
    1.50
     fundamentalist
    1.49
     Athe
    1.47
    Activations Density 0.013%

    No Known Activations