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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23610
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to health insurance coverage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to insurance or healthcare coverage

    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
    geries
    -0.72
     Sabha
    -0.70
    gery
    -0.69
     slightest
    -0.69
    mine
    -0.68
    ffe
    -0.66
    rum
    -0.66
    rir
    -0.66
    ovie
    -0.65
    estamp
    -0.64
    POSITIVE LOGITS
     Coverage
    1.26
     coverage
    1.14
    verage
    0.90
    irtual
    0.85
     cov
    0.81
    oided
    0.78
    orship
    0.78
     COVER
    0.77
    atcher
    0.75
    krit
    0.73
    Activations Density 0.015%

    No Known Activations