© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9054
    Prev
    Next
    INDEX
    Explanations

    words in the Russian language, specifically focusing on the Cyrillic alphabet

    oai_token-act-pair · gpt-3.5-turbo

    references to specific companies or entities, particularly related to transportation services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.77
    cean
    -0.77
    ========
    -0.75
    selage
    -0.70
    cled
    -0.69
    pled
    -0.69
    cised
    -0.68
    fetched
    -0.67
    yip
    -0.67
    phas
    -0.67
    POSITIVE LOGITS
    ÑĮ
    1.18
    а
    1.04
    л
    1.03
    и
    0.97
    е
    0.95
    оÐ
    0.95
    icut
    0.92
    Ñı
    0.90
    alid
    0.89
    о
    0.85
    Activations Density 0.008%

    No Known Activations