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. 2-RES-JB
    6. 16872
    Prev
    Next
    INDEX
    Explanations

    references to the superhero character "Captain America" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Captain" from various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    td
    -0.79
    pher
    -0.75
    itual
    -0.72
    itsch
    -0.71
    âĶģ
    -0.68
    practice
    -0.66
    elf
    -0.65
    20439
    -0.65
    ilateral
    -0.65
    ocene
    -0.64
    POSITIVE LOGITS
     Captain
    1.02
    ĨĴ
    0.88
    Captain
    0.87
     Kidd
    0.81
    berries
    0.80
    berry
    0.78
     Marvel
    0.78
     Marshal
    0.78
     Colonel
    0.77
     Jack
    0.77
    Activations Density 0.009%

    No Known Activations