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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 18808
    Prev
    Next
    INDEX
    Explanations

    numbers and financial terms related to stock market trading

    oai_token-act-pair · gpt-3.5-turbo

    financial metrics and stock market performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.65
     bureaucrats
    -0.65
     subcontract
    -0.63
     Gaia
    -0.61
    lig
    -0.61
     multicultural
    -0.58
     Conserv
    -0.58
    ography
    -0.57
     suffice
    -0.56
     bureaucr
    -0.56
    POSITIVE LOGITS
    daq
    1.13
     trading
    1.10
    DAQ
    0.98
     traded
    0.91
     Shares
    0.91
     midday
    0.90
     Nas
    0.90
     traders
    0.88
     trader
    0.88
     futures
    0.88
    Activations Density 0.187%

    No Known Activations