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

    Neuronpedia

    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. 11-RES-JB
    11. 1721
    Prev
    Next
    INDEX
    Explanations

    mentions of military actions and significant historical events

    oai_token-act-pair · gpt-3.5-turbo

    military actions and related terminologies

    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
     parenting
    -0.83
    Consumer
    -0.80
     Kardash
    -0.79
    obyl
    -0.79
     Transparency
    -0.78
    creator
    -0.77
    Parents
    -0.77
    ilogy
    -0.74
    2012
    -0.74
     Consumer
    -0.73
    POSITIVE LOGITS
     infantry
    1.58
     cavalry
    1.48
     garrison
    1.44
     artillery
    1.42
     battalion
    1.37
     Infantry
    1.35
     flank
    1.34
     platoon
    1.33
     retreating
    1.29
     skirm
    1.28
    Activations Density 0.476%

    No Known Activations