© 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. 8-RES-JB
    11. 17786
    Prev
    Next
    INDEX
    Explanations

    words related to gardening

    oai_token-act-pair · gpt-3.5-turbo

    references to gardens and gardening activities

    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
    nces
    -0.77
    uchin
    -0.75
    phas
    -0.73
    utral
    -0.73
     Lumpur
    -0.72
    ulic
    -0.71
    sem
    -0.69
    viation
    -0.68
    igmat
    -0.67
    emort
    -0.67
    POSITIVE LOGITS
     garden
    1.16
     gardens
    1.09
     gardening
    1.05
     gard
    0.92
     patio
    0.91
     planting
    0.88
    conservancy
    0.88
     Gardens
    0.86
     hose
    0.86
     landsc
    0.84
    Activations Density 0.036%

    No Known Activations