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. 21421
    Prev
    Next
    INDEX
    Explanations

    keywords related to religious or sacred objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to sacred or revered entities and concepts

    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
     Handling
    -0.73
     Tackle
    -0.72
     Tacoma
    -0.71
    rons
    -0.70
    arians
    -0.69
     Ton
    -0.67
     Ross
    -0.66
    atten
    -0.66
    produ
    -0.65
     Transition
    -0.65
    POSITIVE LOGITS
     holy
    3.62
    holy
    2.61
    Holy
    2.39
     Holy
    2.26
     holiest
    2.00
     sacred
    1.97
     pious
    1.40
     saint
    1.32
     Sacred
    1.32
     mystical
    1.30
    Activations Density 0.028%

    No Known Activations