© 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. 9-RES-JB
    11. 10259
    Prev
    Next
    INDEX
    Explanations

    references to the health insurance program Medicare, including discussions around eligibility, costs, and legislation related to it

    oai_token-act-pair · gpt-3.5-turbo

    references to Medicare and its associated policies or programs

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    semble
    -0.80
    */(
    -0.78
    lang
    -0.77
    angers
    -0.76
    othe
    -0.72
    lie
    -0.71
    pole
    -0.70
    unci
    -0.69
    iannopoulos
    -0.68
    worldly
    -0.68
    POSITIVE LOGITS
     Advantage
    1.14
     Benefits
    0.97
     beneficiaries
    0.95
     reimbursement
    0.94
     Payment
    0.90
     prescription
    0.87
     Medicare
    0.85
     Savings
    0.83
     entitle
    0.83
     reimburse
    0.82
    Activations Density 0.029%

    No Known Activations