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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 1279
    Prev
    Next
    INDEX
    Explanations

    the name "Bashar" being discussed in relation to various events and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the Syrian President Bashar al-Assad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OSP
    -0.72
     Edinburgh
    -0.66
     oats
    -0.64
    Recommend
    -0.64
    inburgh
    -0.62
     Pacers
    -0.62
    print
    -0.62
     Hawaiian
    -0.61
    earable
    -0.61
     filings
    -0.61
    POSITIVE LOGITS
     Haf
    1.09
     Assad
    1.06
     Hussein
    1.03
     Tayyip
    0.93
     Abbas
    0.92
     Bashar
    0.91
    Assad
    0.88
    ascus
    0.83
    lers
    0.81
     Rouge
    0.79
    Activations Density 0.018%

    No Known Activations