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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10268
    Prev
    Next
    INDEX
    Explanations

    religious and spiritual terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to spiritual or religious concepts and figures

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

    No Comments

    Negative Logits
     McCl
    -0.89
     headline
    -0.86
     headlines
    -0.84
    Pitt
    -0.83
    olson
    -0.79
     Rudd
    -0.77
    Todd
    -0.74
     BART
    -0.70
     Fitzpatrick
    -0.69
    CDC
    -0.69
    POSITIVE LOGITS
     Meditation
    1.28
    akra
    1.27
     Spiritual
    1.12
     Buddha
    1.08
     Dharma
    1.08
     enlightenment
    1.08
     meditation
    1.06
    spirit
    1.04
     spiritual
    1.04
     mystic
    1.01
    Activations Density 0.537%

    No Known Activations