© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 21766
    Prev
    Next
    INDEX
    Explanations

    decorative elements, such as colors, patterns, and designs

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to decorations and colors

    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
    olit
    -0.80
    lag
    -0.71
    sych
    -0.71
    mediate
    -0.70
    neau
    -0.70
    Leaks
    -0.69
    erate
    -0.67
    IER
    -0.67
    cible
    -0.66
    Limit
    -0.65
    POSITIVE LOGITS
     motif
    1.14
     decorations
    1.07
     adorned
    1.06
     decoration
    1.04
     painted
    1.03
     coloring
    0.99
     tattoos
    0.97
     embro
    0.95
     ornament
    0.95
     ribbon
    0.94
    Activations Density 0.204%

    No Known Activations