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. 10-RES-JB
    6. 9770
    Prev
    Next
    INDEX
    Explanations

    words related to agriculture and farming practices

    oai_token-act-pair · gpt-3.5-turbo

    references to agricultural crops and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gettable
    -0.79
    cester
    -0.73
    ahime
    -0.70
     thous
    -0.69
    ĪĴ
    -0.68
    aldo
    -0.67
     pronoun
    -0.67
    olulu
    -0.66
    gin
    -0.63
    ENA
    -0.62
    POSITIVE LOGITS
     crops
    1.25
     growers
    1.01
    Farm
    0.97
     crop
    0.97
     yields
    0.95
     plants
    0.95
    seed
    0.94
     harvest
    0.92
     farmer
    0.91
     farmers
    0.88
    Activations Density 0.057%

    No Known Activations