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. 0-RES-JB
    6. 14436
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental topics related to oceans and sea-level rise

    oai_token-act-pair · gpt-3.5-turbo

    references to oceans and seas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lder
    -0.76
    lik
    -0.66
    abi
    -0.65
    `
    -0.64
    ue
    -0.63
     Flex
    -0.63
     Match
    -0.62
    flex
    -0.61
    QB
    -0.61
     Fancy
    -0.61
    POSITIVE LOGITS
     oceans
    3.83
     ocean
    2.27
     seas
    2.23
     continents
    1.83
    ceans
    1.80
    Ocean
    1.79
     reefs
    1.64
     rivers
    1.61
     waterways
    1.59
     Seas
    1.59
    Activations Density 0.018%

    No Known Activations