© 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. 4-RES-JB
    6. 24397
    Prev
    Next
    INDEX
    Explanations

    terms related to child care, health, and support

    oai_token-act-pair · gpt-3.5-turbo

    references to children's health and welfare topics

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

    No Comments

    Negative Logits
    pmwiki
    -0.82
    ç
    -0.71
    SpaceEngineers
    -0.69
    士
    -0.68
    isance
    -0.68
    ãĥĥãĥĪ
    -0.68
    д
    -0.68
    rency
    -0.68
    ulence
    -0.67
    ãĤ¨
    -0.66
    POSITIVE LOGITS
     grandchildren
    0.85
     nurse
    0.83
     aged
    0.77
     Adults
    0.75
     Willow
    0.74
     captivity
    0.73
    loe
    0.73
     nursing
    0.70
     kittens
    0.69
     Byron
    0.69
    Activations Density 0.491%

    No Known Activations