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. 0-RES-JB
    6. 22955
    Prev
    Next
    INDEX
    Explanations

    references related to financial terms, specifically "subprime."

    oai_token-act-pair · gpt-3.5-turbo

    references to subprime lending and financial themes related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Collins
    -0.78
     scroll
    -0.66
     license
    -0.66
     notification
    -0.65
     Calendar
    -0.64
     Committee
    -0.63
     tab
    -0.62
     updated
    -0.62
     complications
    -0.62
     details
    -0.61
    POSITIVE LOGITS
    prime
    4.51
    Prime
    2.22
     prime
    1.94
     Prime
    1.47
    prim
    1.09
    terday
    1.07
    annie
    1.04
    mort
    1.03
    factor
    1.00
    venge
    0.97
    Activations Density 0.013%

    No Known Activations