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. 10964
    Prev
    Next
    INDEX
    Explanations

    references to miracles or miraculous occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to miracles and miraculous events

    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
     Sessions
    -0.75
    hing
    -0.66
    ki
    -0.64
    oci
    -0.62
    isson
    -0.61
    members
    -0.61
     Pos
    -0.61
    edin
    -0.59
     views
    -0.58
    encing
    -0.58
    POSITIVE LOGITS
     miracle
    4.21
     miracles
    2.71
     miraculous
    2.54
     Miracle
    2.43
     mirac
    1.62
     wonders
    1.32
     savior
    1.27
     marvel
    1.19
     saint
    1.12
     catastrophe
    1.10
    Activations Density 0.023%

    No Known Activations