© 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. 2-RES-JB
    11. 17149
    Prev
    Next
    INDEX
    Explanations

    mentions of the stock market and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to stock markets and related financial terms

    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
     removable
    -0.90
    ĪĴ
    -0.81
    Ļ½
    -0.77
    Veter
    -0.76
    HCR
    -0.73
    Interstitial
    -0.73
    »Ĵ
    -0.72
    ILE
    -0.72
    ļéĨĴ
    -0.71
    NetMessage
    -0.70
    POSITIVE LOGITS
     hedge
    0.96
     liquidity
    0.91
    ocracy
    0.90
     dynasty
    0.88
     futures
    0.88
    folio
    0.87
    daq
    0.86
     holdings
    0.83
     Securities
    0.83
    stocks
    0.82
    Activations Density 0.199%

    No Known Activations