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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 19729
    Prev
    Next
    INDEX
    Explanations

    keywords related to different types of arts or skills, such as journaling, painting, leadership, and smoking meat

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to the concept of "art."

    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
    wcsstore
    -0.76
    ittees
    -0.71
    hesda
    -0.70
    [[
    -0.69
    ":["
    -0.68
    isd
    -0.67
    è»
    -0.65
    ento
    -0.65
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.65
    NetMessage
    -0.64
    POSITIVE LOGITS
     mankind
    0.79
     humankind
    0.76
     Jesus
    0.72
     Friedrich
    0.70
     globalization
    0.69
     Photography
    0.68
     warfare
    0.68
     humanity
    0.68
     Socialism
    0.66
     course
    0.66
    Activations Density 0.256%

    No Known Activations