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. 9216
    Prev
    Next
    INDEX
    Explanations

    references to vaccines, especially related to HPV

    oai_token-act-pair · gpt-3.5-turbo

    references to vaccines and vaccination-related topics

    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
    rawled
    -0.74
    gre
    -0.70
     Kens
    -0.70
    folk
    -0.69
     Artist
    -0.66
    perial
    -0.65
     Street
    -0.62
    onde
    -0.62
    Artist
    -0.62
    gt
    -0.60
    POSITIVE LOGITS
     vaccine
    3.51
     vaccines
    3.10
     vaccination
    2.89
    vacc
    2.77
     Vacc
    2.75
     vaccinations
    2.66
     vaccinated
    2.51
     vacc
    2.28
     polio
    1.90
     measles
    1.80
    Activations Density 0.029%

    No Known Activations