© 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. 4-RES-JB
    11. 20831
    Prev
    Next
    INDEX
    Explanations

    Russian words with a focus on the letter "д" and various other Cyrillic characters

    oai_token-act-pair · gpt-3.5-turbo

    words or concepts in a specific foreign language, likely Cyrillic

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

    No Comments

    Negative Logits
    ebus
    -0.93
    merce
    -0.82
    pload
    -0.81
    ichita
    -0.80
    atche
    -0.77
    ndra
    -0.77
    neum
    -0.76
    ught
    -0.75
    upiter
    -0.73
    sburg
    -0.73
    POSITIVE LOGITS
    а
    1.17
    и
    1.17
    оÐ
    1.14
    е
    1.06
    о
    1.05
    н
    1.01
    ت
    1.00
    Ùĩ
    0.99
    ا
    0.98
    س
    0.97
    Activations Density 0.009%

    No Known Activations