© 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. 1-RES-JB
    11. 15858
    Prev
    Next
    INDEX
    Explanations

    terms related to children's health and healthcare

    oai_token-act-pair · gpt-3.5-turbo

    references to "Children" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ced
    -1.02
     comm
    -0.71
    CE
    -0.68
    coe
    -0.67
     bis
    -0.66
     cred
    -0.64
    olulu
    -0.64
    utherford
    -0.62
    adena
    -0.61
    zzi
    -0.61
    POSITIVE LOGITS
     Children
    1.25
    children
    1.07
    kids
    0.94
    Children
    0.91
    child
    0.87
     Child
    0.82
     orphans
    0.81
    girls
    0.81
     children
    0.80
     Songs
    0.76
    Activations Density 0.005%

    No Known Activations