© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 12666
    Prev
    Next
    INDEX
    Explanations

    terms related to Turkish politics and Turkish figures such as Recep Tayyip Erdogan

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Turkey and its political figures

    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
     Marty
    -0.76
     LS
    -0.74
    NH
    -0.68
    amins
    -0.68
    atson
    -0.66
     Bain
    -0.66
    venants
    -0.65
    VM
    -0.64
    rine
    -0.64
    dot
    -0.62
    POSITIVE LOGITS
     Turkish
    3.69
    Turkish
    3.37
    Turkey
    2.69
     Turkey
    2.60
     Turks
    2.39
     Armenian
    2.30
     Ankara
    2.30
     Erdogan
    2.26
     Istanbul
    2.21
     Ottoman
    2.18
    Activations Density 0.025%

    No Known Activations