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. 10-RES-JB
    6. 23807
    Prev
    Next
    INDEX
    Explanations

    words related to beliefs and faith

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express belief or faith in various concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detected
    -0.77
    soever
    -0.75
    irable
    -0.71
    isky
    -0.68
    YE
    -0.67
    ISON
    -0.67
    iae
    -0.67
    MAP
    -0.65
    DragonMagazine
    -0.64
    Dispatch
    -0.64
    POSITIVE LOGITS
     miracles
    1.33
     God
    1.03
    clus
    1.00
     reincarn
    0.98
     ghosts
    0.95
     fairness
    0.94
     preserving
    0.93
     miraculous
    0.89
     karma
    0.87
     miracle
    0.87
    Activations Density 0.057%

    No Known Activations