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. 8-RES-JB
    6. 4318
    Prev
    Next
    INDEX
    Explanations

    words related to agriculture and rural life

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to agriculture and agrarian societies

    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
     onward
    -0.69
    phrine
    -0.68
    nings
    -0.63
     balloons
    -0.63
    downs
    -0.61
     craw
    -0.61
     onwards
    -0.60
     numbered
    -0.60
     edges
    -0.59
    eways
    -0.59
    POSITIVE LOGITS
    ulture
    0.87
    ê
    0.81
    ultural
    0.81
    andise
    0.75
    izz
    0.74
    emia
    0.73
    Islamic
    0.71
    ritic
    0.70
    athy
    0.69
    Zen
    0.68
    Activations Density 0.073%

    No Known Activations