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. 11-RES-JB
    6. 18149
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial matters and taxpaying

    oai_token-act-pair · gpt-3.5-turbo

    references to taxpayers and their financial contributions

    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
    quickShipAvailable
    -0.66
    ussen
    -0.64
    java
    -0.64
    arcity
    -0.64
    osite
    -0.63
    apa
    -0.61
    chat
    -0.60
    ealous
    -0.60
    lis
    -0.60
    estation
    -0.59
    POSITIVE LOGITS
    payers
    1.27
     dollars
    1.21
    payer
    1.21
     dime
    1.15
     subsid
    1.14
     taxpayers
    1.08
     taxpayer
    1.07
     Dollars
    1.06
     funded
    1.02
     reimburse
    0.97
    Activations Density 0.049%

    No Known Activations