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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5961
    Prev
    Next
    INDEX
    Explanations

    medical terms and descriptions related to neonatal care

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical or healthcare contexts, particularly in neonatal and physical care scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Americans
    -0.57
    apego
    -0.54
     Israelis
    -0.51
    olicited
    -0.49
     Russians
    -0.49
     protestors
    -0.48
    orsi
    -0.46
     brakes
    -0.45
     Filip
    -0.45
     proponents
    -0.45
    POSITIVE LOGITS
     vicinity
    1.10
     context
    0.95
     attic
    0.93
     drawer
    0.85
     contexts
    0.85
     realm
    0.84
     courtyard
    0.83
     room
    0.83
     guise
    0.82
     area
    0.82
    Activations Density 0.652%

    No Known Activations