© 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. 2-RES-JB
    11. 21568
    Prev
    Next
    INDEX
    Explanations

    mentions of stocks in a financial context

    oai_token-act-pair · gpt-3.5-turbo

    references to stock markets and investments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brotherhood
    -0.78
    BLE
    -0.76
    UTH
    -0.74
    Wheel
    -0.72
    rawdownloadcloneembedreportprint
    -0.70
    ROR
    -0.66
    soever
    -0.64
    displayText
    -0.63
    ATIONAL
    -0.63
    bid
    -0.62
    POSITIVE LOGITS
     stocks
    1.05
    ocks
    0.95
    cape
    0.91
    stocks
    0.89
     shelves
    0.86
    ensical
    0.84
    mith
    0.84
    creen
    0.82
    ettings
    0.82
    utherland
    0.79
    Activations Density 0.009%

    No Known Activations