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. 6922
    Prev
    Next
    INDEX
    Explanations

    words related to mortality and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to mortality and death

    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
    obe
    -0.75
    grab
    -0.74
    Pac
    -0.74
    uzz
    -0.70
    tag
    -0.68
    wire
    -0.67
     Pak
    -0.65
    brew
    -0.65
    wagen
    -0.64
    oun
    -0.64
    POSITIVE LOGITS
     mortality
    3.75
    ortality
    1.78
     deaths
    1.68
     death
    1.53
     fatalities
    1.45
     Deaths
    1.42
     morbid
    1.41
    death
    1.39
     immortality
    1.26
     Mort
    1.26
    Activations Density 0.015%

    No Known Activations