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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20735
    Prev
    Next
    INDEX
    Explanations

    information related to financial matters, specifically focusing on government spending and investments

    oai_token-act-pair · gpt-3.5-turbo

    references to government spending and budget-related metrics

    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
    iquette
    -0.84
     Mock
    -0.75
    uberty
    -0.75
     Philippe
    -0.74
    terness
    -0.73
     Cait
    -0.70
     Ryder
    -0.70
    bart
    -0.70
     Ober
    -0.70
     Sina
    -0.68
    POSITIVE LOGITS
     expenditure
    1.78
     expenditures
    1.77
     spending
    1.77
     budgets
    1.75
     Spending
    1.63
     appropriations
    1.47
     budget
    1.47
     funding
    1.44
     budgetary
    1.44
     taxpayer
    1.39
    Activations Density 0.516%

    No Known Activations