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. 8-RES-JB
    6. 4504
    Prev
    Next
    INDEX
    Explanations

    words related to farming and agriculture

    oai_token-act-pair · gpt-3.5-turbo

    references to agricultural practices and the relationship between farming and food production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verbal
    -0.79
    agram
    -0.79
    ipolar
    -0.78
    FBI
    -0.78
     Rosenstein
    -0.77
     Ghostbusters
    -0.75
     Comey
    -0.75
     hacker
    -0.75
     Cyber
    -0.73
     Wiz
    -0.73
    POSITIVE LOGITS
     farms
    1.44
     crops
    1.41
     pasture
    1.40
     soils
    1.35
     plants
    1.33
     harvest
    1.33
     livestock
    1.33
     plantations
    1.33
     vegetables
    1.32
     harvested
    1.28
    Activations Density 1.091%

    No Known Activations