© 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. 20350
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mint" with varying strength activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Mint."

    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
    interstitial
    -0.90
    ÑĮ
    -0.76
    ouses
    -0.74
    ties
    -0.71
    Ñĭ
    -0.68
     Waterloo
    -0.67
    ements
    -0.66
    à
    -0.66
    uberty
    -0.66
    uador
    -0.65
    POSITIVE LOGITS
     Mint
    1.04
     Seym
    0.94
    inav
    0.83
    ricted
    0.81
    pal
    0.80
    riad
    0.75
     Reader
    0.75
     Dealer
    0.74
     Coins
    0.72
    adan
    0.72
    Activations Density 0.015%

    No Known Activations