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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 15
    Prev
    Next
    INDEX
    Explanations

    keyword or phrases related to credit cards and transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to credit card transactions and related financial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.86
     Atmosp
    -0.75
     Emin
    -0.71
     fract
    -0.67
    ixels
    -0.65
     Modes
    -0.64
    unte
    -0.63
    hower
    -0.63
     Fract
    -0.62
    ovie
    -0.62
    POSITIVE LOGITS
    inals
    1.16
     issuer
    1.02
     debit
    0.94
     swipe
    0.93
    holder
    0.91
    iologist
    0.89
    holders
    0.86
     payment
    0.85
     holder
    0.84
    card
    0.83
    Activations Density 0.031%

    No Known Activations