© 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. 21697
    Prev
    Next
    INDEX
    Explanations

    word pairs related to financial transactions and movements of money

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial transactions and economic activities

    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
    wcsstore
    -0.71
    anship
    -0.70
    endon
    -0.70
    Description
    -0.67
     resemblance
    -0.66
    thood
    -0.65
    rek
    -0.65
    ibe
    -0.63
    iece
    -0.63
     Dating
    -0.62
    POSITIVE LOGITS
     coffers
    1.33
     pockets
    1.27
     mouths
    1.03
     circulation
    0.99
     hands
    0.99
     wallets
    0.97
     warehouses
    0.95
     landfill
    0.93
     prisons
    0.90
     exch
    0.88
    Activations Density 0.292%

    No Known Activations