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. 15830
    Prev
    Next
    INDEX
    Explanations

    food ingredients that can be combined in various recipes

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and elements related to food 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
     Gamergate
    -0.83
    Privacy
    -0.77
     Borders
    -0.70
     Scientology
    -0.69
     DPR
    -0.68
     Academic
    -0.66
    ITNESS
    -0.66
     Contribut
    -0.66
    Student
    -0.65
    bringer
    -0.65
    POSITIVE LOGITS
     cheese
    1.34
     sauce
    1.30
     beans
    1.26
    iflower
    1.25
     squash
    1.18
     tomatoes
    1.18
     noodles
    1.16
     salsa
    1.14
     Sauce
    1.13
     peppers
    1.12
    Activations Density 0.131%

    No Known Activations