© 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. 11-RES-JB
    11. 6729
    Prev
    Next
    INDEX
    Explanations

    words related to finance and economics, specifically focusing on words related to gain, loss, profit, and investment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial gain and loss

    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
    yet
    -0.67
     beginnings
    -0.63
     Frie
    -0.62
    Ò
    -0.62
     kinderg
    -0.62
     Canad
    -0.61
     humanoid
    -0.57
    eworks
    -0.57
    mber
    -0.56
     Cra
    -0.56
    POSITIVE LOGITS
     if
    0.99
     arising
    0.87
     attributable
    0.87
     incurred
    0.84
    loss
    0.84
     losses
    0.81
     stemming
    0.78
     depending
    0.77
     financially
    0.76
     due
    0.76
    Activations Density 0.395%

    No Known Activations