© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 6626
    Prev
    Next
    INDEX
    Explanations

    mentions of breast-related topics, such as breast cancer, breastfeeding, and breast milk

    oai_token-act-pair · gpt-3.5-turbo

    references to breast cancer and breastfeeding

    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
    mble
    -0.68
    eff
    -0.66
     Airbnb
    -0.64
     Emerald
    -0.64
    quickShipAvailable
    -0.64
    $$$$
    -0.64
    redits
    -0.63
    nces
    -0.63
    udos
    -0.61
    âĶģ
    -0.61
    POSITIVE LOGITS
    fed
    1.24
     cancer
    1.20
    mil
    1.16
     milk
    1.10
    feeding
    1.07
    cancer
    1.04
    plate
    1.04
     implants
    1.02
    bone
    1.02
    stroke
    0.97
    Activations Density 0.025%

    No Known Activations