© 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. 19184
    Prev
    Next
    INDEX
    Explanations

    mentions of different religious beliefs or practices

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to religious beliefs and practices

    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
     Velocity
    -0.86
     Overs
    -0.77
     Tackle
    -0.74
     Yards
    -0.74
     Pound
    -0.72
    Mi
    -0.72
    pload
    -0.71
     Prototype
    -0.71
    onde
    -0.71
     Lever
    -0.70
    POSITIVE LOGITS
     religious
    3.34
    religious
    2.79
     Religious
    2.70
     religion
    2.34
     relig
    2.29
     theological
    2.16
     religions
    2.09
     religiously
    2.06
     secular
    1.98
     Religion
    1.96
    Activations Density 0.023%

    No Known Activations