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. 7409
    Prev
    Next
    INDEX
    Explanations

    phrases related to global economic and trade activities

    oai_token-act-pair · gpt-3.5-turbo

    economic and trade-related factors affecting industries

    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
     honorary
    -0.71
     Anniversary
    -0.68
     Elijah
    -0.65
     honorable
    -0.63
     voic
    -0.62
     particulars
    -0.61
     prank
    -0.61
     confir
    -0.60
     Illuminati
    -0.60
     Honor
    -0.60
    POSITIVE LOGITS
     cheaply
    1.30
     economically
    1.00
     cheaper
    0.96
     domestically
    0.95
     efficiently
    0.91
     profitable
    0.88
     inefficient
    0.87
     cheapest
    0.85
     markets
    0.85
    Demand
    0.85
    Activations Density 0.567%

    No Known Activations