© 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. 2-RES-JB
    11. 1459
    Prev
    Next
    INDEX
    Explanations

    names related to the popular character "Minions"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Minions" or its variants

    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
    enegger
    -0.92
    kefeller
    -0.69
    çīĪ
    -0.67
    schild
    -0.66
    atered
    -0.65
    ãģį
    -0.65
    hower
    -0.64
    otle
    -0.64
    llah
    -0.63
     red
    -0.62
    POSITIVE LOGITS
    imal
    1.10
    iatures
    1.00
    utes
    0.94
    istries
    0.94
    aret
    0.91
    erva
    0.90
    imize
    0.88
    neapolis
    0.85
    usc
    0.85
    utation
    0.85
    Activations Density 0.006%

    No Known Activations