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. 24407
    Prev
    Next
    INDEX
    Explanations

    references to comic book superheroes, especially Captain America

    oai_token-act-pair · gpt-3.5-turbo

    references to "Captain America" and associated characters or films

    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
     conven
    -0.69
    mediate
    -0.66
    tem
    -0.65
    eret
    -0.65
     sponsor
    -0.65
    zl
    -0.64
    GBT
    -0.62
     trough
    -0.62
     wee
    -0.62
    housing
    -0.62
    POSITIVE LOGITS
     Awakens
    0.87
    âĦ¢:
    0.86
     trilogy
    0.80
     Armored
    0.80
    ences
    0.79
     Investigations
    0.76
     Creed
    0.75
     Mansion
    0.74
    ®,
    0.74
    ioxide
    0.74
    Activations Density 0.037%

    No Known Activations