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. 10-RES-JB
    6. 17774
    Prev
    Next
    INDEX
    Explanations

    political figures, government positions, and international relations in the context of Turkey

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and governmental entities

    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
     Charleston
    -1.12
     Blacks
    -1.00
     Vermont
    -0.96
     Corvette
    -0.95
     Holden
    -0.94
     Warwick
    -0.92
     Worcester
    -0.90
     Southampton
    -0.88
     Sweeney
    -0.88
     Wilmington
    -0.87
    POSITIVE LOGITS
    ÄŁ
    2.31
    ı
    2.16
     Ankara
    2.15
    ÅŁ
    2.05
    Turkish
    1.96
     Turkish
    1.95
    Turkey
    1.94
     Erdogan
    1.92
     PKK
    1.89
     Erd
    1.88
    Activations Density 0.287%

    No Known Activations