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. 11628
    Prev
    Next
    INDEX
    Explanations

    words related to superheroes

    oai_token-act-pair · gpt-3.5-turbo

    references to superheroes

    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
    hower
    -0.87
    choes
    -0.82
    bah
    -0.81
    chard
    -0.79
    sweet
    -0.78
    imentary
    -0.74
    baugh
    -0.70
    uce
    -0.70
    bris
    -0.69
     Lovely
    -0.69
    POSITIVE LOGITS
     superhero
    0.98
     superheroes
    0.93
     villain
    0.84
     villains
    0.83
     heroes
    0.82
     costumes
    0.81
     comics
    0.80
     costume
    0.77
    hero
    0.76
     powers
    0.76
    Activations Density 0.022%

    No Known Activations