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. 12647
    Prev
    Next
    INDEX
    Explanations

    mentions of submarines in a context that might involve military or nautical themes

    oai_token-act-pair · gpt-3.5-turbo

    references to submarines and related terminology

    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
     Marketable
    -0.80
    place
    -0.79
    giving
    -0.79
    grain
    -0.77
    heet
    -0.76
    eful
    -0.73
    tg
    -0.72
    reads
    -0.72
    kee
    -0.71
     Marijuana
    -0.70
    POSITIVE LOGITS
     submarines
    1.14
     submarine
    1.12
     submar
    0.99
    marine
    0.90
    iltration
    0.87
     stationed
    0.82
     USS
    0.82
     platoon
    0.80
     cables
    0.79
     patrols
    0.77
    Activations Density 0.011%

    No Known Activations