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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20902
    Prev
    Next
    INDEX
    Explanations

    phrases related to wars or military conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to warfare or military-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atel
    -0.80
    ogene
    -0.77
    aminer
    -0.71
    clair
    -0.69
    essee
    -0.68
    chell
    -0.67
    igne
    -0.67
    acle
    -0.66
    hemy
    -0.66
    hedral
    -0.65
    POSITIVE LOGITS
     WAR
    1.17
    rior
    1.03
    NER
    0.93
    WAR
    0.93
    riors
    0.91
    RI
    0.89
    NING
    0.83
    SHIP
    0.81
    ãĤ¼ãĤ¦ãĤ¹
    0.81
     resil
    0.81
    Activations Density 0.009%

    No Known Activations