© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 18819
    Prev
    Next
    INDEX
    Explanations

    mentions of atheism and atheists

    oai_token-act-pair · gpt-3.5-turbo

    references to atheism and atheists

    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
    patch
    -0.79
     Yards
    -0.77
     Lever
    -0.69
    Patch
    -0.67
     Port
    -0.66
    Story
    -0.63
     exported
    -0.63
     Regions
    -0.62
    CL
    -0.62
    Transfer
    -0.61
    POSITIVE LOGITS
     atheist
    3.59
     atheists
    3.41
     atheism
    3.21
     Athe
    2.79
     athe
    2.00
     Dawkins
    1.80
     secular
    1.78
     unbel
    1.71
    athe
    1.69
    religious
    1.46
    Activations Density 0.030%

    No Known Activations