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. 10-RES-JB
    6. 415
    Prev
    Next
    INDEX
    Explanations

    references to Marvel, including characters, movies, and studios

    oai_token-act-pair · gpt-3.5-turbo

    references to Marvel and its related properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chard
    -0.65
     vo
    -0.65
     Ãĸ
    -0.65
    debian
    -0.65
    cki
    -0.64
     spoon
    -0.64
    isons
    -0.63
     Limbaugh
    -0.63
    nil
    -0.62
    ngth
    -0.61
    POSITIVE LOGITS
     Comics
    1.40
     Studios
    1.26
    ous
    1.25
     Cinem
    1.14
    ously
    1.08
     superheroes
    1.02
     Universe
    0.98
     Entertainment
    0.98
     comics
    0.95
     superhero
    0.92
    Activations Density 0.032%

    No Known Activations