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. 10398
    Prev
    Next
    INDEX
    Explanations

    references and information related to conflict and military actions in Yemen

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to geopolitical conflict and terrorism

    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
     Ghostbusters
    -1.09
     Bulgar
    -0.99
     cannabin
    -0.98
    Denver
    -0.93
     Boulder
    -0.92
     bunny
    -0.90
     Romanian
    -0.89
    geist
    -0.88
     Nirvana
    -0.88
     NRS
    -0.87
    POSITIVE LOGITS
     Yemeni
    2.25
     Houth
    2.15
     Yemen
    2.06
     Sana
    1.99
     Aden
    1.83
     Saudi
    1.43
     Riyadh
    1.40
     Oman
    1.38
     AQ
    1.37
     Somalia
    1.36
    Activations Density 0.116%

    No Known Activations