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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 21145
    Prev
    Next
    INDEX
    Explanations

    words related to food items

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of food

    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
     Spectre
    -0.81
    unda
    -0.67
    hire
    -0.64
    ilee
    -0.64
     Lash
    -0.63
    stroke
    -0.63
     Avalanche
    -0.63
    iden
    -0.61
    volt
    -0.61
     Omar
    -0.59
    POSITIVE LOGITS
     foods
    3.44
     Foods
    2.35
    food
    2.09
     food
    2.07
    Food
    2.01
     diets
    2.00
     meals
    1.95
     meats
    1.83
     cuisine
    1.71
     snacks
    1.71
    Activations Density 0.033%

    No Known Activations