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. 11780
    Prev
    Next
    INDEX
    Explanations

    words related to broad or wide-ranging concepts or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    the use of the term "wide" in various contexts referring to broad scope or extent

    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
    ilater
    -0.79
    anamo
    -0.76
    ulia
    -0.72
    Fight
    -0.69
    isons
    -0.69
    ngth
    -0.68
    ourke
    -0.68
    LV
    -0.68
    emis
    -0.68
     Templ
    -0.67
    POSITIVE LOGITS
    wide
    1.12
    sheets
    0.81
     rollout
    0.76
    lining
    0.74
    sheet
    0.73
     worldwide
    0.73
     spectrum
    0.72
     referen
    0.72
     dissemination
    0.71
     scope
    0.70
    Activations Density 0.008%

    No Known Activations