© 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 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. 11-RES-JB
    11. 7496
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to characters and terms from the Star Wars franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to characters and elements from the Star Wars universe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.76
    ball
    -0.74
    ctive
    -0.70
    ivity
    -0.69
    debian
    -0.68
    geoning
    -0.68
    inger
    -0.67
     @@
    -0.67
    iveness
    -0.66
    gency
    -0.66
    POSITIVE LOGITS
     Skywalker
    1.43
     Kenobi
    1.03
     Vader
    1.03
    warm
    0.98
     Obi
    0.83
     Trooper
    0.82
     lightsaber
    0.80
     Cage
    0.79
     Strongh
    0.78
     Tus
    0.76
    Activations Density 0.107%

    No Known Activations