Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 20624
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial terms, specifically focusing on interest rates

    oai_token-act-pair · gpt-3.5-turbo

    references to interest rates and their impact on financial conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cial
    -0.77
    gewater
    -0.69
    llan
    -0.69
    uscript
    -0.68
     Damon
    -0.67
    ELF
    -0.66
    ãĤ¨ãĥ«
    -0.65
    thur
    -0.63
    rome
    -0.63
    apple
    -0.63
    POSITIVE LOGITS
     rates
    1.16
     rate
    1.14
     Rates
    1.00
    Rate
    0.97
     Rate
    0.94
     expense
    0.89
     payments
    0.84
    rate
    0.83
    enza
    0.79
     accrued
    0.77
    Activations Density 0.034%

    No Known Activations