© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8243
    Prev
    Next
    INDEX
    Explanations

    mentions of industrial or urban farming

    oai_token-act-pair · gpt-3.5-turbo

    mentions of farms in various contexts

    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
    IDENT
    -0.70
     symptom
    -0.69
    ensation
    -0.68
    match
    -0.67
     mirror
    -0.67
     AUD
    -0.67
    911
    -0.67
    uit
    -0.67
     match
    -0.66
    verbal
    -0.66
    POSITIVE LOGITS
     farms
    3.91
     farm
    2.45
     Farms
    2.25
    farm
    2.17
    Farm
    2.11
     farming
    2.11
     plantations
    2.10
     farmland
    2.00
     farmers
    1.95
     Farm
    1.75
    Activations Density 0.015%

    No Known Activations