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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 7574
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    specific references and instructions related to food preparation and cooking

    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
    Privacy
    -0.82
    iversity
    -0.79
    Technology
    -0.74
    UX
    -0.74
    thood
    -0.73
    Track
    -0.73
    ythm
    -0.72
    CLASSIFIED
    -0.72
    Level
    -0.71
    Supported
    -0.71
    POSITIVE LOGITS
     mixture
    1.39
     veggies
    1.34
     ingredients
    1.32
     spices
    1.25
     sauce
    1.19
     ingred
    1.19
     batter
    1.17
     skillet
    1.16
     vegetables
    1.14
     dough
    1.14
    Activations Density 0.105%

    No Known Activations