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. 7-RES-JB
    6. 12972
    Prev
    Next
    INDEX
    Explanations

    words related to political entities or actions, specifically focusing on the term "Kremlin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Kremlin" and related geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORGE
    -0.85
    IRD
    -0.82
    ayer
    -0.79
    ICAN
    -0.78
    adoes
    -0.77
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.76
    ministic
    -0.73
    Thom
    -0.72
     Tracy
    -0.70
    ayers
    -0.69
    POSITIVE LOGITS
     rall
    0.95
     Kremlin
    0.90
     annexed
    0.85
     Moscow
    0.83
    ²¾
    0.82
    apo
    0.77
     dictatorship
    0.75
    ascus
    0.74
    Moscow
    0.73
     dictator
    0.73
    Activations Density 0.019%

    No Known Activations