© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1064
    Prev
    Next
    INDEX
    Explanations

    references to the word "mint", likely focusing on the object or organization rather than the flavor

    oai_token-act-pair · gpt-3.5-turbo

    references to "mint" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ake
    -0.73
     Incarn
    -0.65
     Adv
    -0.64
     Soup
    -0.64
     Methodist
    -0.64
     Airbnb
    -0.63
    RAW
    -0.63
    ---------
    -0.62
     voc
    -0.61
    Magikarp
    -0.60
    POSITIVE LOGITS
     Seym
    1.40
    ãĥ¼ãĥĨãĤ£
    0.90
     mint
    0.87
    ulously
    0.83
    marks
    0.83
    oufl
    0.81
    eer
    0.80
    rats
    0.80
    stones
    0.80
    mark
    0.78
    Activations Density 0.017%

    No Known Activations