© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 13123
    Prev
    Next
    INDEX
    Explanations

    terms related to large sums of money, specifically mentioning dollar amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to large amounts of money or financial values

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Oss
    -0.72
    ãĤ¦ãĤ¹
    -0.71
    ydia
    -0.71
    ople
    -0.68
    âĸ¬
    -0.68
     Stru
    -0.67
    leness
    -0.66
     Halls
    -0.66
    ICLE
    -0.64
    reads
    -0.63
    POSITIVE LOGITS
     ($
    1.06
     apiece
    0.96
    -$
    0.96
     worth
    0.94
     annually
    0.93
     sterling
    0.92
    /$
    0.91
     USD
    0.90
     laundering
    0.88
     dollars
    0.88
    Activations Density 0.058%

    No Known Activations