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. 17210
    Prev
    Next
    INDEX
    Explanations

    references to believers and skeptics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to belief and followers

    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
    RAW
    -0.77
    COL
    -0.71
     Liqu
    -0.67
    ony
    -0.64
     Mond
    -0.64
    Board
    -0.64
    artment
    -0.62
    oot
    -0.62
    ONY
    -0.61
     Toxic
    -0.61
    POSITIVE LOGITS
     believers
    3.73
     believer
    2.99
     skeptics
    1.73
     adherents
    1.73
    ievers
    1.63
     atheists
    1.49
     unbel
    1.44
     disbel
    1.41
     proponents
    1.40
     Christians
    1.37
    Activations Density 0.017%

    No Known Activations