© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 477
    Prev
    Next
    INDEX
    Explanations

    words with the root "mint"

    oai_token-act-pair · gpt-4-turbo

    the word "mint" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to mint and minting activities

    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
     Ake
    -0.68
     Rapp
    -0.67
    ---------
    -0.66
    RAW
    -0.64
     Methodist
    -0.64
    Rap
    -0.63
    Magikarp
    -0.63
     Dys
    -0.62
    addock
    -0.62
    argument
    -0.62
    POSITIVE LOGITS
     Seym
    1.41
     mint
    1.10
    ãĥ¼ãĥĨãĤ£
    0.99
    mint
    0.95
     coins
    0.94
     coin
    0.90
    itaire
    0.88
    roman
    0.84
    marks
    0.84
    eer
    0.79
    Activations Density 0.008%

    No Known Activations