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. 3-RES-JB
    6. 15008
    Prev
    Next
    INDEX
    Explanations

    references to the term "Aussie" in text

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group or demographic, particularly related to "Aussie."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iated
    -0.80
    tis
    -0.71
     charact
    -0.71
    Recomm
    -0.70
    raz
    -0.69
    ials
    -0.68
    rooms
    -0.66
     ancest
    -0.66
    Mist
    -0.65
    angering
    -0.64
    POSITIVE LOGITS
    ussie
    0.92
    bilt
    0.85
    hers
    0.85
    iewicz
    0.77
    enegger
    0.77
    ãĤĮ
    0.72
    hew
    0.71
    flix
    0.70
    xon
    0.70
    zsche
    0.69
    Activations Density 0.016%

    No Known Activations