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. 7-RES-JB
    6. 655
    Prev
    Next
    INDEX
    Explanations

    references to the act of growing plants, particularly related to marijuana

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cultivation or growing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.82
    ngth
    -0.78
    ority
    -0.74
    oute
    -0.71
    ensional
    -0.70
    PLIC
    -0.69
    ux
    -0.68
    ĪĴ
    -0.66
    ictional
    -0.66
    plementation
    -0.64
    POSITIVE LOGITS
     vines
    0.83
     indoors
    0.82
     plants
    0.82
     Plants
    0.81
    edIn
    0.79
     vegetables
    0.78
    lings
    0.77
     crops
    0.75
     Farms
    0.75
     trees
    0.74
    Activations Density 0.069%

    No Known Activations