© 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. 8-RES-JB
    11. 12999
    Prev
    Next
    INDEX
    Explanations

    medical terms related to studies on various health conditions, such as HIV infection and MRI scans

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to health and medical research

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    iquette
    -0.92
    tainment
    -0.78
     necessities
    -0.76
     perks
    -0.75
     wrench
    -0.73
    chemy
    -0.72
    ãĥķãĤ©
    -0.72
     amenities
    -0.71
    TextColor
    -0.71
    Charges
    -0.71
    POSITIVE LOGITS
     cohort
    0.99
     patients
    0.94
     Patients
    0.91
     coronary
    0.91
     experimental
    0.91
     adolescents
    0.90
     Alzheimer
    0.89
     diabetic
    0.88
     PLoS
    0.87
     (âĪĴ
    0.85
    Activations Density 0.460%

    No Known Activations