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. 6-RES-JB
    6. 21308
    Prev
    Next
    INDEX
    Explanations

    topics related to international conflicts and political events

    oai_token-act-pair · gpt-3.5-turbo

    topics related to war, investigations, and political conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Soft
    -0.73
    ij士
    -0.71
    onym
    -0.70
    Unix
    -0.68
    typically
    -0.68
    itely
    -0.68
    é¾įå
    -0.68
    tem
    -0.68
     Nun
    -0.66
     Koen
    -0.66
    POSITIVE LOGITS
     debacle
    0.86
     fiasco
    0.80
     bombing
    0.78
     repeal
    0.71
     woes
    0.70
     surge
    0.68
     anniversary
    0.68
     blacklist
    0.67
     bombings
    0.67
     meltdown
    0.66
    Activations Density 0.155%

    No Known Activations