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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19234
    Prev
    Next
    INDEX
    Explanations

    mentions of maternity-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to maternity, paternity, and miscarriage

    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
    rish
    -0.89
    ishing
    -0.89
    nery
    -0.87
    ning
    -0.86
    sworth
    -0.82
    lisher
    -0.82
    mire
    -0.81
    nings
    -0.80
    ioned
    -0.79
    ishes
    -0.78
    POSITIVE LOGITS
     wardrobe
    0.73
    assetsadobe
    0.70
     unfocusedRange
    0.69
    urnal
    0.66
    onduct
    0.66
    helle
    0.66
     maternity
    0.63
     contin
    0.63
    ocaly
    0.62
    porary
    0.62
    Activations Density 0.021%

    No Known Activations