© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13862
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Star Wars" and related entities, such as characters and titles within the Star Wars franchise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Star Wars" franchise

    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
    SPONSORED
    -0.96
    onyms
    -0.93
    onym
    -0.91
    ISON
    -0.88
    inventoryQuantity
    -0.78
    uckland
    -0.75
    aye
    -0.75
    odox
    -0.74
    umbai
    -0.74
    ele
    -0.73
    POSITIVE LOGITS
     Rebels
    1.11
    âĦ¢:
    1.07
     trilogy
    1.06
     Trilogy
    1.01
     Odyssey
    0.98
     Celebration
    0.97
    âĦ¢
    0.96
     Battle
    0.95
     Adventures
    0.94
     Episode
    0.94
    Activations Density 0.049%

    No Known Activations