© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3061
    Prev
    Next
    INDEX
    Explanations

    references to health, safety, and well-being concerns specifically related to children

    oai_token-act-pair · gpt-3.5-turbo

    references to children and their age groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciation
    -0.84
     Heist
    -0.71
    Http
    -0.70
    PO
    -0.69
    ãĥķãĤ©
    -0.68
    ãĥ¢
    -0.65
    APD
    -0.64
     creditor
    -0.63
    Accessory
    -0.63
    ATIVE
    -0.63
    POSITIVE LOGITS
     ages
    1.20
     aged
    1.09
     younger
    1.05
    chool
    1.04
     Ages
    1.02
     age
    0.97
     toddlers
    0.93
    children
    0.93
     kindergarten
    0.92
     preschool
    0.89
    Activations Density 0.096%

    No Known Activations