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. 19557
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific geographic location, specifically Rhode Island

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Rhode Island and its locations

    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
    ocene
    -0.76
    hammad
    -0.75
     accur
    -0.75
    ueller
    -0.75
    eared
    -0.69
    uchin
    -0.68
    ramid
    -0.67
    ogene
    -0.65
    eger
    -0.64
    verb
    -0.63
    POSITIVE LOGITS
     Islanders
    1.01
     Island
    0.97
     Rhode
    0.96
    sylvania
    0.80
     Oaks
    0.80
     RI
    0.78
     Beach
    0.76
    esses
    0.71
    Shield
    0.71
     Hood
    0.71
    Activations Density 0.011%

    No Known Activations