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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 6595
    Prev
    Next
    INDEX
    Explanations

    phrases related to health insurance coverage, including details about plans and payments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health insurance coverage and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMAGES
    -0.87
    çīĪ
    -0.80
    ovie
    -0.73
     Atmosp
    -0.73
    DragonMagazine
    -0.71
     Assass
    -0.70
    ograp
    -0.68
     PLA
    -0.66
    orically
    -0.66
    iewicz
    -0.66
    POSITIVE LOGITS
    amacare
    1.36
     premiums
    1.14
    payer
    1.05
     beneficiaries
    1.04
     reimburse
    1.03
     Medicaid
    1.02
     providers
    0.98
     insurers
    0.98
     rebate
    0.97
     eligibility
    0.96
    Activations Density 0.123%

    No Known Activations