Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11011
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "mint" or the word "mint" itself, potentially related to coins, flavors, or facilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "mint" or minting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idal
    -0.89
     prol
    -0.70
    cells
    -0.70
    Cole
    -0.69
    osa
    -0.68
     Trap
    -0.65
    rieved
    -0.64
    Accessory
    -0.64
    lift
    -0.63
    akable
    -0.62
    POSITIVE LOGITS
     Mint
    3.80
     mint
    3.79
    mint
    2.75
     Coin
    1.15
     coins
    1.12
     Coins
    1.06
     coin
    1.01
     Strawberry
    1.00
     Cinnamon
    0.99
     Armory
    0.92
    Activations Density 0.017%

    No Known Activations