© 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. 0-RES-JB
    11. 7538
    Prev
    Next
    INDEX
    Explanations

    mentions related to infants and infant-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to infants and newborns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gre
    -0.73
    vl
    -0.70
    wall
    -0.68
    untled
    -0.67
    ablishment
    -0.67
     vend
    -0.67
    INESS
    -0.66
    iller
    -0.66
    route
    -0.65
    fx
    -0.65
    POSITIVE LOGITS
     infants
    3.20
     infant
    3.02
     newborn
    2.89
     babies
    2.69
     toddlers
    2.24
     toddler
    2.10
     baby
    1.94
     fetus
    1.89
     infancy
    1.86
     unborn
    1.78
    Activations Density 0.032%

    No Known Activations