© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1320
    Prev
    Next
    INDEX
    Explanations

    text related to political events, conflicts, and attacks in specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to violent or aggressive actions in geopolitical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     someday
    -0.95
     glim
    -0.84
     zoning
    -0.83
     bumps
    -0.75
    aukee
    -0.75
     renov
    -0.73
     upstairs
    -0.73
     apprentices
    -0.72
     downtown
    -0.71
     remod
    -0.70
    POSITIVE LOGITS
    Statement
    1.11
    AFP
    1.10
    BBC
    1.04
    Russia
    0.97
    Moscow
    0.97
    Terror
    0.96
     Whilst
    0.96
     Wikileaks
    0.95
    Reuters
    0.94
     Retrieved
    0.94
    Activations Density 0.704%

    No Known Activations