Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 377
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the Vatican

    oai_token-act-pair · gpt-3.5-turbo

    references to the Vatican and its related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -0.81
    ãģ¦
    -0.81
    pring
    -0.80
    awks
    -0.79
    served
    -0.76
    eworld
    -0.76
    Haw
    -0.75
    mental
    -0.75
    haw
    -0.73
    nesota
    -0.73
    POSITIVE LOGITS
    arium
    0.89
     Vatican
    0.89
    Leaks
    0.86
     Embassy
    0.82
     Patriarch
    0.80
     bureaucracy
    0.80
     pope
    0.77
     brass
    0.77
    itary
    0.76
     decre
    0.75
    Activations Density 0.009%

    No Known Activations