© 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. 11-RES-JB
    11. 22045
    Prev
    Next
    INDEX
    Explanations

    phrases related to baking ingredients or instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to baking-related terms and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.79
    ial
    -0.78
     Paddock
    -0.76
    iveness
    -0.76
     Investigative
    -0.69
    draw
    -0.67
     Fenrir
    -0.65
     Gat
    -0.62
    uations
    -0.62
     Pont
    -0.61
    POSITIVE LOGITS
     soda
    0.98
    lite
    0.96
    pillar
    0.86
     cookies
    0.82
     dough
    0.78
     oven
    0.78
     goods
    0.76
     bread
    0.76
     bake
    0.75
    ModLoader
    0.75
    Activations Density 0.062%

    No Known Activations