Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16711
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical conflicts and power dynamics

    oai_token-act-pair · gpt-3.5-turbo

    references to international military influence and conflict

    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
     Walton
    -0.70
     dads
    -0.68
     sle
    -0.67
     Hobby
    -0.65
     typew
    -0.65
     Trout
    -0.65
    Kids
    -0.63
     Edison
    -0.62
     lottery
    -0.62
    College
    -0.62
    POSITIVE LOGITS
     abroad
    1.55
    Syria
    1.28
     internationally
    1.25
     domestically
    1.24
     overseas
    1.24
     milit
    1.22
     Syria
    1.17
     territ
    1.14
     diplom
    1.13
     Iran
    1.09
    Activations Density 0.451%

    No Known Activations