© 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. 10-RES-JB
    11. 20628
    Prev
    Next
    INDEX
    Explanations

    references to Syrian President Bashar al-Assad

    oai_token-act-pair · gpt-3.5-turbo

    references to the Syrian president, Bashar al-Assad, and related political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckland
    -0.99
     Wilde
    -0.94
     Honolulu
    -0.93
     Garfield
    -0.90
     Cricket
    -0.89
     Perth
    -0.89
    deck
    -0.88
     bowling
    -0.88
     Phelps
    -0.87
     Bonds
    -0.86
    POSITIVE LOGITS
     Assad
    2.12
     Syrian
    2.06
    Assad
    2.03
    Syrian
    2.03
     Idlib
    1.95
     Syrians
    1.94
     Aleppo
    1.93
     Damascus
    1.93
     Homs
    1.92
    Syria
    1.91
    Activations Density 0.370%

    No Known Activations