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. 1-RES-JB
    6. 17435
    Prev
    Next
    INDEX
    Explanations

    references to the term "Life"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Life" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.90
    mented
    -0.78
    ãĥĺ
    -0.78
     Cosponsors
    -0.77
    MENTS
    -0.76
    uned
    -0.76
    IAL
    -0.73
    akedown
    -0.72
    ãĥ¼ãĤ¯
    -0.69
    sonian
    -0.69
    POSITIVE LOGITS
    bringer
    0.91
    guards
    0.90
     Life
    0.89
    guard
    0.81
     expectancy
    0.80
    blood
    0.80
    Life
    0.78
    life
    0.77
    boats
    0.77
    mares
    0.76
    Activations Density 0.015%

    No Known Activations