© 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. 71
    Prev
    Next
    INDEX
    Explanations

    phrases related to honoring and recognizing people for their sacrifices and heroic actions

    oai_token-act-pair · gpt-3.5-turbo

    references to soldiers and acts of valor or sacrifice

    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
    ilibrium
    -0.81
     Sims
    -0.80
    Discussion
    -0.78
    Studio
    -0.72
     Collider
    -0.69
    mitter
    -0.68
    Sche
    -0.68
    Lot
    -0.68
    loop
    -0.66
    CHAT
    -0.66
    POSITIVE LOGITS
     bravery
    1.64
     heroism
    1.56
     valiant
    1.51
     courage
    1.45
     martyr
    1.45
     brave
    1.45
     heroic
    1.44
     sacrifice
    1.42
     courageous
    1.38
     sacrificed
    1.37
    Activations Density 0.624%

    No Known Activations