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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 7748
    Prev
    Next
    INDEX
    Explanations

    Keywords related to economic indicators and financial matters, particularly consumer prices, labor, government debt, and housing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic indicators and financial metrics

    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
     NCT
    -0.76
     Navajo
    -0.76
     Scientology
    -0.72
     Jeanne
    -0.72
    irlf
    -0.70
    £ı
    -0.70
     Ern
    -0.69
     Starfleet
    -0.69
     Crew
    -0.68
     Vet
    -0.67
    POSITIVE LOGITS
     inflation
    1.33
     prices
    1.24
     incomes
    1.15
     deflation
    1.14
     growth
    1.14
     expenditure
    1.11
     stagnation
    1.10
     Prices
    1.08
     unemployment
    1.08
     expenditures
    1.06
    Activations Density 0.238%

    No Known Activations