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. 7959
    Prev
    Next
    INDEX
    Explanations

    phrases related to dangerous geopolitical situations and potential conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to threats of nuclear conflict or war

    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
    thank
    -0.80
    Favorite
    -0.76
    EY
    -0.74
     Detail
    -0.69
    ometry
    -0.67
    ertation
    -0.63
    elle
    -0.62
    plex
    -0.62
    Goal
    -0.61
    Score
    -0.61
    POSITIVE LOGITS
     collapse
    1.22
     catastrophe
    1.21
     Armageddon
    1.13
    riots
    1.13
     disaster
    1.11
     catastrophic
    1.11
     annihilation
    1.07
     irreversible
    1.04
     bloodshed
    1.04
     doom
    1.03
    Activations Density 0.338%

    No Known Activations