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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    6. 9489
    Prev
    Next
    INDEX
    Explanations

    information related to childbirth and newborn babies

    oai_token-act-pair · gpt-3.5-turbo

    references to newborns and infant-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ACTIONS
    -0.78
    ãĤ¶
    -0.72
    iliate
    -0.70
    ãĥķãĤ¡
    -0.69
    ontent
    -0.67
     redes
    -0.66
    rank
    -0.65
    OPE
    -0.64
    senal
    -0.64
    stanbul
    -0.64
    POSITIVE LOGITS
     careg
    1.03
     captivity
    0.95
     caregivers
    0.87
     womb
    0.85
    Dad
    0.83
     nursery
    0.81
     nursing
    0.78
     anesthesia
    0.77
     diaper
    0.76
     nurse
    0.75
    Activations Density 0.745%

    No Known Activations