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. 18445
    Prev
    Next
    INDEX
    Explanations

    references to religious figures, particularly pastors

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the title "pastor."

    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
    urat
    -0.83
    plets
    -0.69
    axy
    -0.65
    EMS
    -0.65
    thin
    -0.64
     Carbuncle
    -0.62
    اÙĦ
    -0.62
    xp
    -0.60
    ibaba
    -0.60
     Petroleum
    -0.60
    POSITIVE LOGITS
     pastor
    0.99
     Pastor
    0.93
    esses
    0.88
     preached
    0.87
    iffe
    0.81
     preach
    0.80
    angel
    0.79
    ess
    0.78
     evangel
    0.76
    angelo
    0.76
    Activations Density 0.021%

    No Known Activations