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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18852
    Prev
    Next
    INDEX
    Explanations

    titles, names, and terms related to the Star Wars franchise

    oai_token-act-pair · gpt-3.5-turbo

    titles and terms related to 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
    aukee
    -1.00
     Paragu
    -0.87
    elaide
    -0.87
    Portland
    -0.85
     hurd
    -0.83
     Couch
    -0.82
    nil
    -0.82
    Jenn
    -0.81
    Denver
    -0.80
    fet
    -0.80
    POSITIVE LOGITS
     Jedi
    2.15
     lightsaber
    2.02
     droid
    1.93
     Darth
    1.90
     Skywalker
    1.90
     Obi
    1.87
     Leia
    1.86
     Sith
    1.80
     Vader
    1.78
     Kenobi
    1.74
    Activations Density 0.133%

    No Known Activations