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. 0-RES-JB
    6. 10766
    Prev
    Next
    INDEX
    Explanations

    words related to background checks, especially emphasizing the action of performing background checks

    oai_token-act-pair · gpt-3.5-turbo

    references to background checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adena
    -0.69
    oric
    -0.68
    omed
    -0.66
     cruc
    -0.66
    uma
    -0.65
    assetsadobe
    -0.65
    inth
    -0.62
    okia
    -0.61
    ras
    -0.60
    offer
    -0.58
    POSITIVE LOGITS
     checks
    3.94
     Checks
    2.85
    checks
    2.81
     check
    2.33
     checking
    1.91
    check
    1.76
     checked
    1.74
    checking
    1.65
    CHECK
    1.49
     Checking
    1.49
    Activations Density 0.011%

    No Known Activations