© 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. 10-RES-JB
    11. 20540
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of universality

    oai_token-act-pair · gpt-3.5-turbo

    mentions of universal concepts, particularly related to health and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regon
    -0.88
    ritz
    -0.73
    sbm
    -0.71
    utenant
    -0.71
    manship
    -0.66
    --------------------------------------------------------
    -0.66
    uden
    -0.65
    Ö¼
    -0.65
    mosp
    -0.65
    mond
    -0.64
    POSITIVE LOGITS
    ised
    1.25
    ized
    1.24
    isable
    1.22
    izable
    1.20
    isation
    1.18
    ization
    1.17
    itarian
    1.10
    izing
    1.07
    isations
    1.00
    izes
    1.00
    Activations Density 0.037%

    No Known Activations