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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 10393
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Assad" in a context related to politics and conflict

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Syrian leader Bashar al-Assad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.89
     Tolkien
    -0.79
     RTX
    -0.75
    Lex
    -0.74
    itialized
    -0.73
     Niet
    -0.72
    VERTIS
    -0.72
     Edinburgh
    -0.72
    Pokemon
    -0.72
    CRE
    -0.72
    POSITIVE LOGITS
     regime
    1.04
     Hussein
    1.03
    ascus
    0.96
    Assad
    0.95
     regimes
    0.90
     himself
    0.86
    pin
    0.85
     Jinping
    0.84
     overth
    0.84
    pins
    0.82
    Activations Density 0.049%

    No Known Activations