© 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. 11-RES-JB
    11. 20481
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to pregnancy and its consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to pregnancy and pregnant women

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.93
    olulu
    -0.81
    opol
    -0.73
    phony
    -0.69
    DragonMagazine
    -0.67
    ioxide
    -0.67
    coe
    -0.66
    ugu
    -0.65
     guiActiveUnfocused
    -0.65
    entin
    -0.65
    POSITIVE LOGITS
     miscar
    1.02
     miscarriage
    0.98
     pregnancy
    0.93
     ultrasound
    0.90
     uter
    0.88
     pregnancies
    0.88
    imester
    0.88
     heartbeat
    0.88
     uterus
    0.87
     gestation
    0.84
    Activations Density 0.069%

    No Known Activations