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

    Neuronpedia

    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. 8206
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Turkey

    oai_token-act-pair · gpt-3.5-turbo

    references to Turkey

    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
     MC
    -0.72
     LS
    -0.70
     Byr
    -0.66
     sol
    -0.65
     lum
    -0.65
    die
    -0.64
    inventoryQuantity
    -0.64
     phys
    -0.64
     matt
    -0.64
     Briggs
    -0.64
    POSITIVE LOGITS
     Turkey
    3.65
    Turkey
    3.44
    Turkish
    2.68
     Ankara
    2.63
     Turkish
    2.62
     Istanbul
    2.31
     Erdogan
    2.26
     Turks
    2.12
    stanbul
    1.98
     Armenia
    1.93
    Activations Density 0.011%

    No Known Activations