© 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. 1-RES-JB
    11. 24228
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "Rogue."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Rogue."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.80
    enance
    -0.78
    urrency
    -0.77
    omo
    -0.76
    ilk
    -0.76
    aple
    -0.75
    useum
    -0.72
    ming
    -0.72
    mitt
    -0.71
    advert
    -0.69
    POSITIVE LOGITS
     Rogue
    1.17
     Trader
    1.00
    Rogue
    0.95
     Trooper
    0.82
    esses
    0.80
    DragonMagazine
    0.78
     Squadron
    0.73
    pedia
    0.72
     Awakens
    0.70
    blade
    0.69
    Activations Density 0.006%

    No Known Activations