© 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. 1-RES-JB
    11. 24268
    Prev
    Next
    INDEX
    Explanations

    topics related to finance and monetary affairs

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of finance

    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
    76561
    -0.75
    imus
    -0.75
    onew
    -0.69
    dayName
    -0.67
     Jenner
    -0.65
     Kore
    -0.65
     Cosponsors
    -0.65
    avering
    -0.63
    vil
    -0.62
    Rated
    -0.62
    POSITIVE LOGITS
     finance
    1.06
     financing
    0.84
     mathemat
    0.84
     guru
    0.81
     laundering
    0.80
     lender
    0.78
    ament
    0.76
    ashtra
    0.74
     affairs
    0.73
    itures
    0.73
    Activations Density 0.006%

    No Known Activations