© 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. 3-RES-JB
    11. 24179
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious denominations and beliefs, particularly focusing on Evangelical Christianity and Jehovah's Witnesses

    oai_token-act-pair · gpt-3.5-turbo

    references to religious affiliations and beliefs, particularly those related to Jehovah's Witnesses and Evangelical Christianity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cedented
    -0.83
     captcha
    -0.72
    shown
    -0.68
    æ©
    -0.67
     Steal
    -0.67
     rink
    -0.65
    Downloadha
    -0.65
     Bagg
    -0.64
     NP
    -0.64
     Lans
    -0.63
    POSITIVE LOGITS
     scriptures
    1.17
     scripture
    1.08
     Scriptures
    1.07
     theology
    1.05
     teachings
    1.01
     Bible
    0.98
     communion
    0.95
     bible
    0.95
     fundamentalist
    0.94
     Scripture
    0.93
    Activations Density 0.110%

    No Known Activations