© 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. 7-RES-JB
    11. 2192
    Prev
    Next
    INDEX
    Explanations

    words related to concepts of grace, mercy, and kindness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of grace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hedral
    -0.67
    algia
    -0.66
    ocus
    -0.64
    aeda
    -0.64
    omething
    -0.63
    rogen
    -0.61
     Regulatory
    -0.60
     Argon
    -0.60
     iodine
    -0.58
     Lei
    -0.58
    POSITIVE LOGITS
    fully
    1.49
    ful
    1.24
    fulness
    1.20
    ibility
    1.01
    FUL
    1.00
    full
    0.91
    ifully
    0.86
    ments
    0.83
    ously
    0.82
    combe
    0.80
    Activations Density 0.024%

    No Known Activations