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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 15210
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Luke"

    oai_token-act-pair · gpt-3.5-turbo

    the character "Luke" across various contexts, particularly in reference to media or narratives

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

    No Comments

    Negative Logits
    ãĤ¢ãĥ«
    -0.83
    ursed
    -0.78
    Ùħ
    -0.72
    ktop
    -0.72
    awaru
    -0.70
    gency
    -0.70
    ãĤ½
    -0.69
     Parenthood
    -0.69
     pregn
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.68
    POSITIVE LOGITS
     Skywalker
    1.55
    warm
    1.42
     Cage
    1.10
     Vader
    0.95
    lihood
    0.93
     Luke
    0.93
    avin
    0.91
    Luke
    0.84
     Obi
    0.82
    antine
    0.81
    Activations Density 0.004%

    No Known Activations