© 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. 10-RES-JB
    11. 11191
    Prev
    Next
    INDEX
    Explanations

    terms related to money and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of money and financial crimes, particularly money laundering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Minor
    -0.68
    ICLE
    -0.64
     abdom
    -0.61
    SPA
    -0.60
    COMPLE
    -0.60
     Fuk
    -0.59
     Comfort
    -0.59
    Hug
    -0.59
     Ary
    -0.58
     Historic
    -0.58
    POSITIVE LOGITS
     laundering
    1.61
    bags
    1.19
    flow
    1.00
    making
    0.99
    aundering
    0.93
    bag
    0.92
    flows
    0.92
     laund
    0.90
     flows
    0.87
     lenders
    0.85
    Activations Density 0.052%

    No Known Activations