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. 8212
    Prev
    Next
    INDEX
    Explanations

    references to the Christian faith or Christian-related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Christian" in various contexts

    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
    Downloadha
    -0.80
    æ©
    -0.78
    ariat
    -0.77
    ðĿ
    -0.72
    obbies
    -0.71
    ounge
    -0.70
    frames
    -0.70
    skirts
    -0.69
    handed
    -0.68
    hots
    -0.68
    POSITIVE LOGITS
     missionaries
    0.92
     Bale
    0.91
     theolog
    0.81
     fundamentalist
    0.80
     faith
    0.77
     missionary
    0.76
     denominations
    0.76
    ization
    0.76
    ophe
    0.76
     faiths
    0.74
    Activations Density 0.019%

    No Known Activations