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. 10625
    Prev
    Next
    INDEX
    Explanations

    references to churches or religious institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "church."

    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
     thin
    -0.71
     equival
    -0.66
     repeat
    -0.65
     yield
    -0.65
     terminal
    -0.64
     radiant
    -0.64
     terminals
    -0.64
     ID
    -0.63
     res
    -0.63
     calculus
    -0.62
    POSITIVE LOGITS
    church
    4.77
    Church
    1.73
    uckland
    1.40
    mington
    1.10
    castle
    1.08
    street
    1.08
     Auckland
    1.06
    aucus
    1.05
    NZ
    1.05
     Canterbury
    1.01
    Activations Density 0.015%

    No Known Activations