© 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. 11-RES-JB
    11. 7122
    Prev
    Next
    INDEX
    Explanations

    mentions of drones in various contexts such as law enforcement, professional use, safety, regulations, and controversies

    oai_token-act-pair · gpt-3.5-turbo
    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
     Cohn
    -0.86
     Florence
    -0.84
     Cavs
    -0.81
     Lust
    -0.80
    Greek
    -0.80
     Knicks
    -0.80
     Bosh
    -0.77
     Angelo
    -0.76
    isSpecialOrderable
    -0.75
    âĸº
    -0.75
    POSITIVE LOGITS
     drone
    2.49
     drones
    2.37
     Drone
    2.35
     unmanned
    1.97
     FAA
    1.60
     aerial
    1.57
    rones
    1.49
     airspace
    1.48
     Predator
    1.47
     Aerial
    1.47
    Activations Density 0.263%

    No Known Activations