© 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. 1-RES-JB
    11. 9369
    Prev
    Next
    INDEX
    Explanations

    words related to financial terms, in particular words related to dividends

    oai_token-act-pair · gpt-3.5-turbo

    terms related to investments, particularly focusing on dividends and ETF (Exchange-Traded Fund) concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olog
    -0.75
    gel
    -0.73
    aque
    -0.72
    ten
    -0.72
    nee
    -0.71
    sonian
    -0.68
    ordan
    -0.65
     Homeless
    -0.65
    ================================================================
    -0.64
    atell
    -0.64
    POSITIVE LOGITS
     dividends
    1.56
     dividend
    1.31
     reinvest
    0.87
     sacrific
    0.84
     gobl
    0.83
     payout
    0.83
    ratulations
    0.82
     income
    0.82
     horm
    0.79
     earnings
    0.78
    Activations Density 0.008%

    No Known Activations