© 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. 4-RES-JB
    11. 10711
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "interest", particularly in the context of financial or economic discussions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to interest rates

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

    No Comments

    Negative Logits
    \\\\\\\\
    -0.81
    女
    -0.75
    oÄŁ
    -0.74
    \\\\
    -0.72
    ãĤ¨ãĥ«
    -0.71
    rome
    -0.70
    nen
    -0.69
    ãĥ´
    -0.69
    llan
    -0.67
    ffe
    -0.67
    POSITIVE LOGITS
     rate
    0.97
     rates
    0.96
     expense
    0.89
    rate
    0.85
     Rates
    0.82
    Rate
    0.82
    enza
    0.81
    iculty
    0.80
     interest
    0.79
     dues
    0.77
    Activations Density 0.018%

    No Known Activations