© 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. 2-RES-JB
    11. 23656
    Prev
    Next
    INDEX
    Explanations

    references to the name "Luke", particularly in relation to sports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Luke."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¢ãĥ«
    -0.80
    itect
    -0.76
    ktop
    -0.74
    ursed
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.69
    gency
    -0.68
    Ùħ
    -0.67
    OWER
    -0.63
    ãĥķãĤ©
    -0.63
     pregn
    -0.63
    POSITIVE LOGITS
     Skywalker
    1.55
    warm
    1.34
     Cage
    1.12
     Luke
    1.03
     Vader
    0.98
    avin
    0.94
    lihood
    0.90
    Luke
    0.88
     Obi
    0.84
    antine
    0.82
    Activations Density 0.003%

    No Known Activations