© 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 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. 0-RES-JB
    11. 9749
    Prev
    Next
    INDEX
    Explanations

    references to money-related terms and topics

    oai_token-act-pair · gpt-3.5-turbo

    references to money and financial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fen
    -0.71
     veget
    -0.69
     density
    -0.68
     display
    -0.66
     tolerant
    -0.65
     dracon
    -0.64
     dens
    -0.64
     gen
    -0.63
     cone
    -0.63
    prot
    -0.63
    POSITIVE LOGITS
     Money
    3.84
    Money
    3.18
    money
    2.86
     money
    2.14
    ONEY
    1.62
     Cash
    1.58
     Dollars
    1.58
     Funds
    1.50
     Profit
    1.48
     Wealth
    1.45
    Activations Density 0.012%

    No Known Activations