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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 18229
    Prev
    Next
    INDEX
    Explanations

    economic terms related to debt and GDP ratios

    oai_token-act-pair · gpt-3.5-turbo

    key financial metrics related to national debt and GDP ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     audition
    -0.80
     testers
    -0.80
     scouts
    -0.79
    paio
    -0.72
     prank
    -0.70
     groom
    -0.70
     Koen
    -0.69
     novice
    -0.69
     scouting
    -0.69
    Arcade
    -0.69
    POSITIVE LOGITS
     GDP
    1.85
     Gross
    1.21
     (%
    1.20
     GN
    1.19
     OECD
    1.18
     nominal
    1.09
     Debt
    1.08
     gross
    1.07
     CPI
    1.07
     Expend
    1.05
    Activations Density 0.339%

    No Known Activations