© 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. 6-RES-JB
    11. 22681
    Prev
    Next
    INDEX
    Explanations

    numeric values related to large amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    references to financial amounts, particularly in the context of billions and trillions of dollars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.92
    alys
    -0.87
    é¾įå
    -0.83
    geist
    -0.74
    ãĤ¦ãĤ¹
    -0.73
    agen
    -0.73
     Oss
    -0.72
    ydia
    -0.71
    ãĤ±
    -0.70
    former
    -0.70
    POSITIVE LOGITS
     dollars
    1.07
     dollar
    0.96
    dollar
    0.87
     worth
    0.87
     USD
    0.85
     purs
    0.83
     earners
    0.82
     enterprises
    0.80
     payout
    0.80
     Dollars
    0.79
    Activations Density 0.037%

    No Known Activations