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. 11-RES-JB
    6. 8346
    Prev
    Next
    INDEX
    Explanations

    mentions of marriage and divorce-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to marriage, divorce, and related legal or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scourge
    -0.92
    monton
    -0.84
    zai
    -0.82
     Blizz
    -0.81
     Keane
    -0.81
    ACC
    -0.80
     Blaster
    -0.80
    osaurus
    -0.79
    zin
    -0.78
    otin
    -0.77
    POSITIVE LOGITS
     marriages
    2.20
     marriage
    2.12
     marital
    2.03
     divorce
    2.02
    married
    2.00
     Marriage
    1.99
     divor
    1.98
     married
    1.98
     marrying
    1.93
     marry
    1.92
    Activations Density 0.552%

    No Known Activations