© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 2466
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Assad" in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to Bashar al-Assad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Edinburgh
    -0.86
     Gutenberg
    -0.81
    inburgh
    -0.76
    osit
    -0.74
     Starship
    -0.74
    print
    -0.74
    PsyNetMessage
    -0.73
    sie
    -0.73
     Honolulu
    -0.72
    visory
    -0.72
    POSITIVE LOGITS
    Assad
    1.22
     Assad
    1.22
     mosqu
    1.14
    ascus
    1.11
     regime
    1.07
     regimes
    1.02
     rall
    0.97
     Bashar
    0.95
     airstrikes
    0.87
     helicop
    0.86
    Activations Density 0.006%

    No Known Activations