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. 10503
    Prev
    Next
    INDEX
    Explanations

    references to income distribution and tax rates, particularly focusing on the top earners

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth distribution and tax policies affecting the top income brackets

    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
    DragonMagazine
    -0.69
    images
    -0.67
     Reincarnated
    -0.65
     Testing
    -0.64
    fresh
    -0.63
    matic
    -0.63
    wake
    -0.63
    åŃ
    -0.62
     Signs
    -0.61
    warm
    -0.61
    POSITIVE LOGITS
     earners
    1.36
     percentile
    1.26
     incomes
    1.20
     income
    1.15
     wealthiest
    1.11
     quint
    1.06
     brackets
    1.05
     richest
    1.03
     households
    1.03
     bracket
    0.95
    Activations Density 0.123%

    No Known Activations