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. 4-RES-JB
    6. 23727
    Prev
    Next
    INDEX
    Explanations

    the word "prevalence"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rates and frequency of events or conditions

    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
    ebus
    -1.03
    iverse
    -0.94
    erm
    -0.76
    imb
    -0.71
    ulkan
    -0.70
    pired
    -0.69
     Sector
    -0.68
    outer
    -0.68
    overe
    -0.67
    wagen
    -0.67
    POSITIVE LOGITS
     preval
    0.92
     prevalence
    0.91
     rates
    0.90
     occurrence
    0.90
     incidence
    0.88
     Rates
    0.81
     (%)
    0.80
     rate
    0.71
     percentages
    0.71
     Rate
    0.71
    Activations Density 0.047%

    No Known Activations