Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19628
    Prev
    Next
    INDEX
    Explanations

    references to the Vietnam War

    oai_token-act-pair · gpt-3.5-turbo

    references to Vietnam, including its history and cultural aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bolt
    -0.88
    heet
    -0.75
    Scotland
    -0.71
     Finch
    -0.70
     macOS
    -0.69
    onne
    -0.68
    furt
    -0.68
     Luthor
    -0.67
     Cobb
    -0.67
     Horowitz
    -0.67
    POSITIVE LOGITS
     Airways
    1.05
     Nguyen
    0.97
     Buddhist
    0.91
     Buddh
    0.91
    orea
    0.86
     Airlines
    0.85
     Laos
    0.84
    utan
    0.83
     Cambod
    0.81
     Cambodia
    0.80
    Activations Density 0.061%

    No Known Activations