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. 3-RES-JB
    6. 11930
    Prev
    Next
    INDEX
    Explanations

    terms related to theology and theologians

    oai_token-act-pair · gpt-3.5-turbo

    terms related to theology and theological concepts

    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
    berman
    -0.79
    egg
    -0.71
     Quit
    -0.66
     Garrison
    -0.65
    ãģ¦
    -0.64
     Pension
    -0.64
    vous
    -0.64
     Kessler
    -0.63
     captcha
    -0.61
    XT
    -0.60
    POSITIVE LOGITS
    istries
    0.95
    istry
    0.91
     theolog
    0.90
     theology
    0.88
    ology
    0.86
    etics
    0.86
    ological
    0.84
    ciples
    0.83
     theological
    0.82
    ians
    0.80
    Activations Density 0.008%

    No Known Activations