© 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. 9-RES-JB
    11. 22938
    Prev
    Next
    INDEX
    Explanations

    statements about military actions, sources, and attacks

    oai_token-act-pair · gpt-3.5-turbo

    reported statements about military activities and related incidents

    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
     Founders
    -0.81
    bill
    -0.79
     Millennials
    -0.78
    etsy
    -0.73
    ãĤ¦ãĤ¹
    -0.70
     ADA
    -0.70
    otin
    -0.69
     millennials
    -0.69
     Cary
    -0.69
    aukee
    -0.67
    POSITIVE LOGITS
     Nato
    1.11
     Reuters
    1.03
     Kurdish
    1.01
     Islamist
    0.96
     Xin
    0.96
     Ankara
    0.96
     UNHCR
    0.96
     Jazeera
    0.96
     AFP
    0.93
     YPG
    0.93
    Activations Density 0.701%

    No Known Activations