© 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. 11-RES-JB
    11. 20769
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical conflicts and military actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geopolitical entities and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ftime
    -0.84
    ãĤ´ãĥ³
    -0.80
    emetery
    -0.76
    Timeout
    -0.76
    ertation
    -0.74
    VERTISEMENT
    -0.73
    thood
    -0.72
    ãĥ¼ãĥ«
    -0.71
    ength
    -0.69
    bnb
    -0.69
    POSITIVE LOGITS
     Soviets
    1.33
     Russians
    1.29
     rebels
    1.23
     Iranians
    1.18
     Kurds
    1.15
     separatists
    1.15
     Taliban
    1.13
     Nazis
    1.12
     insurgents
    1.11
     feds
    1.09
    Activations Density 0.166%

    No Known Activations