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. 27
    Prev
    Next
    INDEX
    Explanations

    the name "Assad" within text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Bashar al-Assad and references to his role in governance and conflict

    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
     Gutenberg
    -0.95
    print
    -0.91
     Edinburgh
    -0.89
    owler
    -0.85
    WARD
    -0.81
    inburgh
    -0.80
    itialized
    -0.78
    osit
    -0.75
    sie
    -0.74
    ION
    -0.74
    POSITIVE LOGITS
    Assad
    1.10
     regime
    1.09
     Assad
    1.03
    ascus
    1.02
     regimes
    0.94
     Hussein
    0.85
     airstrikes
    0.84
     dictatorship
    0.83
     Bashar
    0.82
     captivity
    0.81
    Activations Density 0.019%

    No Known Activations