© 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. 9-RES-JB
    11. 16007
    Prev
    Next
    INDEX
    Explanations

    words related to Turkish or Middle Eastern names and locations

    oai_token-act-pair · gpt-3.5-turbo

    elements related to Turkish culture and language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Polaris
    -0.77
     Appalach
    -0.76
     Cena
    -0.71
     Spartans
    -0.70
     Spartan
    -0.69
     Jericho
    -0.69
     Surviv
    -0.69
    olly
    -0.68
     Peel
    -0.66
     Watson
    -0.66
    POSITIVE LOGITS
    oÄŁ
    1.30
    ı
    1.20
    istani
    1.18
     Tayyip
    1.10
    ÄŁ
    1.06
    oÄŁan
    1.05
    ÅŁ
    1.02
     Erd
    0.96
    lar
    0.87
     Ãĸ
    0.84
    Activations Density 0.055%

    No Known Activations