© 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. 3-RES-JB
    11. 20074
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the stock market

    oai_token-act-pair · gpt-3.5-turbo

    references to stock market concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ECA
    -0.82
    accompanied
    -0.77
    ILE
    -0.74
    HCR
    -0.71
    NetMessage
    -0.70
    igenous
    -0.68
    ĨĴ
    -0.68
    Female
    -0.68
    UV
    -0.66
    sonian
    -0.66
    POSITIVE LOGITS
    daq
    1.15
     volatility
    1.11
     liquidity
    1.01
     holdings
    0.90
    folio
    0.89
     fluctuations
    0.87
     hedge
    0.87
     futures
    0.84
     forecasting
    0.84
    rencies
    0.83
    Activations Density 0.073%

    No Known Activations