Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 24098
    Prev
    Next
    INDEX
    Explanations

    words related to drones

    oai_token-act-pair · gpt-3.5-turbo

    references to drones and their use or impact

    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
    hof
    -0.85
     Cumber
    -0.84
    rosso
    -0.76
     Magicka
    -0.75
    orie
    -0.71
    uations
    -0.70
    Ͻ
    -0.69
     Neh
    -0.69
     Pep
    -0.68
    ento
    -0.67
    POSITIVE LOGITS
     drone
    1.22
     drones
    1.14
     unmanned
    1.01
     aircraft
    1.01
    Deploy
    0.95
     aerial
    0.93
     pilots
    0.93
     Drone
    0.91
     pilot
    0.90
     strike
    0.90
    Activations Density 0.042%

    No Known Activations