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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 12409
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions of the Affordable Care Act (ACA)

    oai_token-act-pair · gpt-3.5-turbo

    references to the Affordable Care Act (ACA)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.77
    court
    -0.68
    Else
    -0.66
    via
    -0.65
     Dynam
    -0.65
    lighting
    -0.64
    translation
    -0.62
    ths
    -0.62
    protein
    -0.61
     Flavoring
    -0.61
    POSITIVE LOGITS
    ACA
    1.28
    amacare
    0.92
     ACA
    0.85
     resc
    0.75
     Gould
    0.73
    BRE
    0.68
    eus
    0.66
    azel
    0.65
    enei
    0.64
    ageddon
    0.64
    Activations Density 0.007%

    No Known Activations