© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1792
    Prev
    Next
    INDEX
    Explanations

    food-related terms, particularly those related to veganism

    oai_token-act-pair · gpt-3.5-turbo

    references to veganism and vegetarianism

    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
     Transmission
    -0.77
     Thro
    -0.74
    bolt
    -0.73
    Scope
    -0.71
     Clock
    -0.67
     Replay
    -0.67
     Citadel
    -0.66
    Engineers
    -0.66
     Hur
    -0.66
     Towers
    -0.64
    POSITIVE LOGITS
     vegan
    3.66
     Vegan
    3.31
     vegetarian
    2.71
     Veg
    1.97
     gluten
    1.93
     tofu
    1.68
     Paleo
    1.67
     veget
    1.59
    Ve
    1.53
     Veget
    1.52
    Activations Density 0.024%

    No Known Activations