© 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. 0-RES-JB
    11. 20560
    Prev
    Next
    INDEX
    Explanations

    terms related to craftsmanship or craft beer

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "craft" in relation to brewing and craftsmanship

    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
     Mub
    -0.76
     Mubarak
    -0.74
    gor
    -0.70
    atin
    -0.70
     Laden
    -0.69
     Liberia
    -0.67
     Statement
    -0.67
    ilion
    -0.67
     Zimbabwe
    -0.64
    opoulos
    -0.64
    POSITIVE LOGITS
     craft
    4.01
     Craft
    2.54
     crafts
    2.39
    craft
    2.31
    Craft
    1.91
     crafting
    1.75
     Crafting
    1.31
     crafted
    1.30
    crafted
    1.23
     artisan
    1.18
    Activations Density 0.023%

    No Known Activations