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. 14279
    Prev
    Next
    INDEX
    Explanations

    the word "staple" along with terms related to being fundamental or essential

    oai_token-act-pair · gpt-3.5-turbo

    the term "staple" and its variations in different contexts, indicating essential elements or components

    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
    odore
    -0.93
     nomine
    -0.78
    ysis
    -0.77
    ept
    -0.75
    zbollah
    -0.74
    oping
    -0.73
    TPPStreamerBot
    -0.71
    peror
    -0.70
    cember
    -0.70
    hner
    -0.70
    POSITIVE LOGITS
     staples
    0.85
    ollar
    0.83
    Jet
    0.83
     staple
    0.80
     Meal
    0.80
    ãĥŁ
    0.75
    marks
    0.73
    ãĥ¥
    0.73
    icals
    0.72
    cliffe
    0.71
    Activations Density 0.045%

    No Known Activations