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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7154
    Prev
    Next
    INDEX
    Explanations

    references to paintings or artworks

    oai_token-act-pair · gpt-3.5-turbo

    references to paintings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nir
    -0.79
    reme
    -0.77
    reek
    -0.76
    ornia
    -0.74
    aucus
    -0.72
    cgi
    -0.72
    aspx
    -0.71
    abad
    -0.71
    UU
    -0.70
    DN
    -0.70
    POSITIVE LOGITS
     painter
    1.14
     paintings
    1.12
     depicting
    1.06
     painting
    1.03
     artwork
    0.91
    wright
    0.91
     Painting
    0.88
     portraits
    0.87
     portraying
    0.85
    isans
    0.85
    Activations Density 0.021%

    No Known Activations