© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2381
    Prev
    Next
    INDEX
    Explanations

    instances of medical conditions or injuries in a hospital setting

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    details related to injuries and medical conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ynchronous
    -0.83
    oppable
    -0.83
    icip
    -0.71
     Respons
    -0.70
    istas
    -0.68
     ACTIONS
    -0.67
     quotas
    -0.66
    earch
    -0.66
     schedules
    -0.66
     Nept
    -0.65
    POSITIVE LOGITS
     wounds
    1.49
     amput
    1.41
     bruising
    1.39
     bruises
    1.38
     swollen
    1.35
     stitches
    1.30
     wound
    1.30
     pierced
    1.29
     fracture
    1.28
     scars
    1.27
    Activations Density 0.367%

    No Known Activations