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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18290
    Prev
    Next
    INDEX
    Explanations

    financial terms related to fees, charges, and payments

    oai_token-act-pair · gpt-3.5-turbo

    financial and fee-related terms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    mosp
    -0.61
    heastern
    -0.59
    ovie
    -0.59
    jiang
    -0.59
    ouver
    -0.58
    nian
    -0.57
    abal
    -0.57
    Pierre
    -0.57
    ãĤ¨ãĥ«
    -0.56
    POSITIVE LOGITS
     coupons
    0.73
     reimbursement
    0.69
     Discount
    0.68
     refund
    0.68
     debit
    0.67
     payable
    0.67
     rebate
    0.66
     Fees
    0.65
     USPS
    0.65
     fees
    0.64
    Activations Density 1.378%

    No Known Activations