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. 8-RES-JB
    6. 16216
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures in the context of international relations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific political figures, particularly focusing on Syrian President Bashar al-Assad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CG
    -0.70
     verified
    -0.66
     precinct
    -0.65
    anwhile
    -0.65
     posit
    -0.62
    acebook
    -0.61
    OPLE
    -0.61
     MOT
    -0.61
     underscore
    -0.60
     storefront
    -0.59
    POSITIVE LOGITS
    Assad
    1.01
    Islam
    1.00
    su
    0.98
    Lago
    0.96
    Ma
    0.93
    Su
    0.91
    Iss
    0.89
    Han
    0.88
    Hu
    0.87
    Pierre
    0.86
    Activations Density 0.029%

    No Known Activations