© 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. 20641
    Prev
    Next
    INDEX
    Explanations

    phrases related to spending money or using finances

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial expenditures

    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
    soType
    -0.93
    externalActionCode
    -0.92
    ãĤ¼ãĤ¦ãĤ¹
    -0.73
    andem
    -0.71
    urally
    -0.71
    é»Ĵ
    -0.69
    amiya
    -0.68
    ãĤī
    -0.68
    ailable
    -0.67
    DragonMagazine
    -0.67
    POSITIVE LOGITS
     upkeep
    1.08
     renovations
    1.08
     researching
    1.01
     improving
    1.00
     lobbying
    0.99
     research
    0.98
     educating
    0.98
     renov
    0.95
     upgrading
    0.94
     maintaining
    0.92
    Activations Density 0.127%

    No Known Activations