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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 14129
    Prev
    Next
    INDEX
    Explanations

    mentions of the Syrian President Bashar Assad

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures associated with the Syrian government, specifically Bashar al-Assad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Magic
    -0.75
    Magic
    -0.66
    SD
    -0.61
    ENN
    -0.61
     GF
    -0.60
    EE
    -0.59
    phia
    -0.59
     library
    -0.59
    pe
    -0.59
     discs
    -0.58
    POSITIVE LOGITS
     Assad
    3.49
    Assad
    3.13
     Bashar
    2.60
     Syrian
    1.95
    Syrian
    1.92
    Syria
    1.90
     Damascus
    1.90
     Syrians
    1.87
     Gaddafi
    1.87
     Aleppo
    1.77
    Activations Density 0.016%

    No Known Activations