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. 3-RES-JB
    6. 22427
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fraud" and related terms within documents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fraud and fraudulent activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    area
    -0.80
    Duration
    -0.74
     adaptations
    -0.67
    accompan
    -0.67
     inspiration
    -0.66
    ä
    -0.66
     duty
    -0.64
    çĦ
    -0.63
     sunrise
    -0.62
     experimental
    -0.61
    POSITIVE LOGITS
    raud
    1.43
    ulent
    1.11
     Fraud
    0.80
    gage
    0.77
    ware
    0.77
    ulence
    0.77
    piracy
    0.77
    razil
    0.75
    vertising
    0.75
     skim
    0.72
    Activations Density 0.032%

    No Known Activations