© 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. 8-RES-JB
    6. 23754
    Prev
    Next
    INDEX
    Explanations

    information related to votes and percentages in agriculture

    oai_token-act-pair · gpt-3.5-turbo

    references to food categories and nutritional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.90
    hower
    -0.85
    nces
    -0.77
    witz
    -0.77
    phalt
    -0.77
    ICAN
    -0.72
    ospace
    -0.71
    swer
    -0.71
    yss
    -0.71
    FontSize
    -0.71
    POSITIVE LOGITS
     Bai
    0.78
     exha
    0.70
    Ĭ±
    0.67
     Kuro
    0.63
     Highlander
    0.62
     Marketable
    0.62
     Mechdragon
    0.62
    Parameter
    0.61
     punishing
    0.59
     disciplinary
    0.59
    Activations Density 0.145%

    No Known Activations