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. 2-RES-JB
    6. 4633
    Prev
    Next
    INDEX
    Explanations

    mentions of the Turkish President Recep Tayyip Erdogan

    oai_token-act-pair · gpt-3.5-turbo

    references to the political figure Erdogan and his government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Plymouth
    -0.70
    Ö¼
    -0.69
     Wales
    -0.69
    ãģ¦
    -0.69
    PASS
    -0.69
    Irish
    -0.69
    hew
    -0.68
    imilar
    -0.68
     Daytona
    -0.68
    Scotland
    -0.67
    POSITIVE LOGITS
     Erdogan
    1.22
    istani
    1.07
     Tayyip
    1.06
    oÄŁan
    1.06
    oÄŁ
    0.98
     Jinping
    0.89
     Recep
    0.85
    oglu
    0.84
    jriwal
    0.83
     Erd
    0.82
    Activations Density 0.011%

    No Known Activations