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. 4-RES-JB
    6. 23390
    Prev
    Next
    INDEX
    Explanations

    words related to safety measures or precautions

    oai_token-act-pair · gpt-3.5-turbo

    references to safety measures and precautions

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

    No Comments

    Negative Logits
    ettle
    -0.75
    zie
    -0.72
     Roses
    -0.68
    peak
    -0.67
    KER
    -0.64
    hner
    -0.63
    versions
    -0.63
    cart
    -0.62
    Beer
    -0.61
    league
    -0.60
    POSITIVE LOGITS
     precaution
    1.21
    autions
    1.09
    ary
    1.03
     precautions
    1.01
    ously
    0.93
    azard
    0.91
    inventoryQuantity
    0.85
     safeguards
    0.78
    urous
    0.77
    icity
    0.77
    Activations Density 0.013%

    No Known Activations