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. 2-RES-JB
    6. 20235
    Prev
    Next
    INDEX
    Explanations

    references to religious ceremonies, particularly baptisms

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to baptism and religious practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eq
    -0.81
    enegger
    -0.81
    utenant
    -0.77
    edy
    -0.77
     Eisen
    -0.71
     Entertainment
    -0.71
    berman
    -0.71
    enberg
    -0.70
    nil
    -0.68
     Cyborg
    -0.68
    POSITIVE LOGITS
     baptism
    1.46
     bapt
    1.42
     baptized
    1.20
     Bapt
    1.02
    ificial
    0.79
    istry
    0.75
    asca
    0.75
     fide
    0.74
     rites
    0.73
    alog
    0.72
    Activations Density 0.018%

    No Known Activations