© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2386
    Prev
    Next
    INDEX
    Explanations

    information related to agriculture, farming, and specific crops like barley and soybeans

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases related to agricultural practices and plant cultivation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    rontal
    -0.77
    ebin
    -0.76
    yrinth
    -0.73
    DCS
    -0.69
    PsyNetMessage
    -0.69
    awaru
    -0.68
    agnar
    -0.67
    ãĤ¡
    -0.66
    ADRA
    -0.66
     Anger
    -0.66
    POSITIVE LOGITS
     harvested
    1.60
     planted
    1.48
     grown
    1.43
     harvest
    1.41
     harvesting
    1.29
     cultivated
    1.28
     flowering
    1.27
     seeds
    1.22
     irrig
    1.21
     Seeds
    1.21
    Activations Density 0.338%

    No Known Activations