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. 17824
    Prev
    Next
    INDEX
    Explanations

    ingredients or cooking-related words in recipes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific items or recipes

    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
    nings
    -0.78
    arson
    -0.74
    andum
    -0.73
    witz
    -0.71
    isms
    -0.71
    occup
    -0.69
    adata
    -0.67
    ussen
    -0.67
    lev
    -0.66
    anamo
    -0.66
    POSITIVE LOGITS
     lovely
    0.91
     guy
    0.86
     lowly
    0.85
     amazing
    0.85
     nifty
    0.83
     particular
    0.83
     gorgeous
    0.83
     handy
    0.79
     sucker
    0.78
     adorable
    0.78
    Activations Density 0.219%

    No Known Activations