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. 8637
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and payments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of payment or pay-related concepts

    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
     wand
    -0.76
     Twilight
    -0.69
     Wand
    -0.68
     whisk
    -0.65
     lucid
    -0.65
     recess
    -0.64
     Mystic
    -0.64
     curled
    -0.63
     Sorceress
    -0.60
     Hamm
    -0.60
    POSITIVE LOGITS
    pay
    4.15
    Pay
    2.39
    payment
    2.34
    paid
    1.78
    paying
    1.77
    cash
    1.57
     Pay
    1.57
     pay
    1.52
     PAY
    1.52
     Payments
    1.32
    Activations Density 0.019%

    No Known Activations