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. 8366
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to sketching or drawings

    oai_token-act-pair · gpt-3.5-turbo

    references to sketches and sketching

    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
    rogens
    -0.77
    undai
    -0.74
    erenn
    -0.74
    judicial
    -0.74
    inion
    -0.73
    relations
    -0.64
    Pear
    -0.64
    respect
    -0.63
     bom
    -0.62
    iqueness
    -0.62
    POSITIVE LOGITS
     sketch
    1.29
     sketches
    1.29
     Sketch
    1.04
    eers
    0.91
    Artist
    0.83
    BOOK
    0.83
    igans
    0.81
     Drawing
    0.81
    enegger
    0.80
    smanship
    0.79
    Activations Density 0.005%

    No Known Activations