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. 4778
    Prev
    Next
    INDEX
    Explanations

    words related to characters and elements from the Star Wars universe

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Star Wars" universe, particularly focusing on key characters and elements of the saga

    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
     Vog
    -0.72
    gency
    -0.70
     Zig
    -0.66
     Ou
    -0.66
    arten
    -0.65
    FUN
    -0.65
    Ü
    -0.64
     IGF
    -0.64
    urated
    -0.64
    uments
    -0.62
    POSITIVE LOGITS
     Skywalker
    1.35
     Vader
    1.12
     Kenobi
    1.08
     lightsaber
    0.93
    acca
    0.92
     Leia
    0.86
    actic
    0.85
     Rebels
    0.81
    film
    0.80
     guiActiveUn
    0.79
    Activations Density 0.049%

    No Known Activations