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. 11-RES-JB
    6. 17927
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and statistics

    oai_token-act-pair · gpt-3.5-turbo

    key economic indicators and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.98
     Canaver
    -0.92
    Buzz
    -0.81
    DragonMagazine
    -0.80
     Lovecraft
    -0.79
     Comet
    -0.75
     Doodle
    -0.74
     Bigfoot
    -0.73
     Valhalla
    -0.73
     Birch
    -0.71
    POSITIVE LOGITS
     GDP
    1.74
     OECD
    1.50
     GN
    1.30
     Gross
    1.28
     gross
    1.25
     labour
    1.23
     nominal
    1.22
     expenditure
    1.21
     exports
    1.17
     incomes
    1.15
    Activations Density 0.474%

    No Known Activations