Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6315
    Prev
    Next
    INDEX
    Explanations

    instances related to the usage or mention of taxpayer money

    oai_token-act-pair · gpt-3.5-turbo

    references to taxpayers and taxpayer money

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    apa
    -0.69
    quickShipAvailable
    -0.65
     Scouting
    -0.64
    appa
    -0.63
    Church
    -0.63
    lime
    -0.63
    occ
    -0.61
    azi
    -0.61
     Chef
    -0.60
     Signal
    -0.60
    POSITIVE LOGITS
    payers
    1.26
     dollars
    1.17
     taxpayers
    1.14
     subsid
    1.13
    payer
    1.10
     taxpayer
    1.01
     dime
    0.98
     Dollars
    0.96
     subsidized
    0.95
     subsidies
    0.95
    Activations Density 0.033%

    No Known Activations