© 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. 1-RES-JB
    11. 14252
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific fictional character or franchise with "Min" and a following number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity named "Minions."

    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
    -0.78
    atered
    -0.69
    kefeller
    -0.65
     flu
    -0.65
     revolving
    -0.64
     red
    -0.63
    å§
    -0.62
    ãģį
    -0.61
    otle
    -0.61
    llah
    -0.61
    POSITIVE LOGITS
    imal
    1.00
    iatures
    0.96
    neapolis
    0.96
    nesota
    0.93
    imize
    0.91
    aret
    0.88
     Min
    0.88
    istries
    0.86
    utation
    0.84
    utes
    0.82
    Activations Density 0.004%

    No Known Activations