© 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 EvalsExportsinterp-engineNEWAPI 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. 20742
    Prev
    Next
    INDEX
    Explanations

    references to healthcare and health insurance policies and programs

    oai_token-act-pair · gpt-3.5-turbo

    references to government and healthcare policy regarding insurance access and assistance for low-income individuals

    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
    matter
    -0.89
    Dialogue
    -0.86
     Subtle
    -0.84
    wcsstore
    -0.83
    ãĥķãĤ©
    -0.78
    angelo
    -0.76
     Carbuncle
    -0.72
    DragonMagazine
    -0.70
    backer
    -0.69
    xon
    -0.69
    POSITIVE LOGITS
     seniors
    1.22
     pregnant
    1.16
     undocumented
    1.15
     uninsured
    1.15
     unmarried
    1.15
     retirees
    1.13
     teenagers
    1.12
     elderly
    1.12
     mothers
    1.10
     spouses
    1.10
    Activations Density 0.331%

    No Known Activations