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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11513
    Prev
    Next
    INDEX
    Explanations

    the word "master" along with some context like "stroke," "race," "pieces," "mind," and "craftsman."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "master"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.79
    IDER
    -0.74
    DEN
    -0.65
    enegger
    -0.64
     retirees
    -0.64
    tics
    -0.62
    hedon
    -0.62
    ople
    -0.61
    vernment
    -0.61
    gm
    -0.60
    POSITIVE LOGITS
    pieces
    1.39
    mind
    1.14
    piece
    1.14
    class
    0.98
    stroke
    0.96
    fully
    0.95
    classes
    0.95
    work
    0.91
    ful
    0.86
    minded
    0.85
    Activations Density 0.021%

    No Known Activations