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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 19914
    Prev
    Next
    INDEX
    Explanations

    instructions for cooking or baking, specifically related to cooling and drying periods

    oai_token-act-pair · gpt-3.5-turbo

    cooking instructions that involve cooling and refrigerating food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     awarding
    -0.65
    èĢħ
    -0.62
    assault
    -0.61
    grave
    -0.61
    zilla
    -0.59
    059
    -0.59
    thro
    -0.59
     Fatal
    -0.58
    女
    -0.58
     tragically
    -0.57
    POSITIVE LOGITS
     refriger
    1.20
     fridge
    1.05
     refrigerator
    1.05
     overnight
    1.04
    riger
    1.04
     cooled
    1.02
     humidity
    1.02
     chilled
    1.00
     dried
    0.99
     moisture
    0.98
    Activations Density 0.171%

    No Known Activations