© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4660
    Prev
    Next
    INDEX
    Explanations

    historical events and political actions related to specific countries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    questions and discussions related to geopolitical issues and U.S. foreign policy actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    earchers
    -0.63
     sequential
    -0.62
     Signature
    -0.61
     workload
    -0.60
    folio
    -0.59
     Performance
    -0.59
    raft
    -0.58
     performer
    -0.57
     accessibility
    -0.57
     Fitness
    -0.56
    POSITIVE LOGITS
    Iran
    1.25
    Assad
    1.25
     NATO
    1.23
    Syria
    1.23
     Saddam
    1.22
    Iraq
    1.21
     Iraqis
    1.18
    Terror
    1.16
    Germany
    1.16
    Turkey
    1.15
    Activations Density 1.229%

    No Known Activations