© 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. 13621
    Prev
    Next
    INDEX
    Explanations

    titles or references related to the "Star Wars" franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to "Star Wars" titles and related media

    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
    raped
    -0.70
    zl
    -0.69
    grass
    -0.69
    */(
    -0.66
    gart
    -0.64
     horizont
    -0.62
    achable
    -0.62
    ilts
    -0.62
    rity
    -0.61
    rence
    -0.61
    POSITIVE LOGITS
    axies
    0.94
    interstitial
    0.80
     Discovery
    0.77
    iland
    0.76
    æĸ¹
    0.73
    ĨĴ
    0.72
     Telescope
    0.70
     Universe
    0.69
     Galaxy
    0.66
     Origins
    0.64
    Activations Density 0.069%

    No Known Activations