© 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. 18969
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the country or people of Turkey

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Turk" and its variations

    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
    inventoryQuantity
    -0.72
    console
    -0.69
    []
    -0.69
     MC
    -0.68
     NEC
    -0.68
     LC
    -0.67
     DARK
    -0.67
     BCC
    -0.66
     Nebula
    -0.65
     null
    -0.63
    POSITIVE LOGITS
     Turk
    4.37
    Tur
    2.21
     Turks
    2.12
     Uzbek
    1.87
    zbek
    1.49
     Armen
    1.44
     Taj
    1.43
     Turkish
    1.40
     Kyr
    1.39
     Azerbaijan
    1.39
    Activations Density 0.031%

    No Known Activations