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. 15564
    Prev
    Next
    INDEX
    Explanations

    connections between various countries and conflicts, particularly involving Iran, Iraq, and related issues

    oai_token-act-pair · gpt-3.5-turbo

    topics related to geopolitical conflicts and regions, particularly involving the Middle East and entities like Iran and Iraq

    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
     glim
    -0.79
     tast
    -0.72
     clerks
    -0.71
     coaster
    -0.71
    earable
    -0.71
    issance
    -0.70
     remem
    -0.70
     audi
    -0.69
     antioxid
    -0.69
     Ratings
    -0.68
    POSITIVE LOGITS
     Kazakhstan
    1.38
     Albania
    1.32
     Afghanistan
    1.29
     Syria
    1.26
     Laos
    1.25
     Indonesia
    1.25
     Belarus
    1.22
     Ukraine
    1.21
     Kosovo
    1.21
     Philippines
    1.20
    Activations Density 0.321%

    No Known Activations