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. 11-RES-JB
    6. 2994
    Prev
    Next
    INDEX
    Explanations

    information related to discounts, prices, and monetary transactions

    oai_token-act-pair · gpt-3.5-turbo

    financial and discount-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ùĩ
    -0.55
    hatt
    -0.54
    idem
    -0.54
     undersc
    -0.54
    ankind
    -0.53
    oward
    -0.52
     Cyr
    -0.52
    Í
    -0.52
     epidem
    -0.50
     humankind
    -0.50
    POSITIVE LOGITS
     coupon
    1.23
     coupons
    1.22
     rebate
    1.20
     refund
    1.19
     payment
    1.12
     refunds
    1.11
     PayPal
    1.10
     discounts
    1.09
     Payments
    1.06
     prepaid
    1.06
    Activations Density 0.629%

    No Known Activations