© 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. 10-RES-JB
    11. 16030
    Prev
    Next
    INDEX
    Explanations

    information related to historical wars, events, and locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific wars and historical conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.82
    blog
    -0.78
    ply
    -0.77
     commenters
    -0.75
    healthy
    -0.73
     customers
    -0.72
    blogs
    -0.72
     biomark
    -0.72
    stem
    -0.72
     retailers
    -0.70
    POSITIVE LOGITS
     invasion
    1.46
     uprising
    1.42
     annexation
    1.32
     conquest
    1.32
     war
    1.29
     liberation
    1.29
     rebellion
    1.28
     hostilities
    1.27
     overthrow
    1.26
     revolutions
    1.25
    Activations Density 0.429%

    No Known Activations