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. 9-RES-JB
    6. 16822
    Prev
    Next
    INDEX
    Explanations

    terms related to soil and its properties

    oai_token-act-pair · gpt-3.5-turbo

    references to soil health and its impact on the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lear
    -0.80
    pload
    -0.70
    yright
    -0.69
    xes
    -0.69
     Pist
    -0.68
    cffffcc
    -0.66
    uscript
    -0.66
    士
    -0.62
     departures
    -0.62
     Bers
    -0.61
    POSITIVE LOGITS
     moisture
    1.05
     flora
    0.87
     fertility
    0.87
     microbes
    0.85
     mound
    0.84
     soil
    0.83
     soils
    0.81
     fungi
    0.80
    grain
    0.79
     pH
    0.78
    Activations Density 0.040%

    No Known Activations