Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1587
    Prev
    Next
    INDEX
    Explanations

    descriptions related to visual art including the mention of specific elements like graphic, design, print, and illustration

    oai_token-act-pair · gpt-3.5-turbo

    references to artwork and illustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    few
    -0.71
    ften
    -0.71
    ishops
    -0.67
    CE
    -0.66
    rir
    -0.66
    atal
    -0.65
    lig
    -0.64
    lat
    -0.64
    zee
    -0.64
     Contra
    -0.63
    POSITIVE LOGITS
     artwork
    1.45
     galleries
    1.02
     paintings
    0.99
     depicting
    0.98
     Thumbnails
    0.94
     gallery
    0.93
     art
    0.92
    heet
    0.91
     IMAGES
    0.90
    works
    0.90
    Activations Density 0.013%

    No Known Activations