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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 1196
    Prev
    Next
    INDEX
    Explanations

    references to drone activity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of drones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pep
    -0.84
     Cumber
    -0.72
     Doyle
    -0.71
     Digest
    -0.71
    orie
    -0.71
     Sacrament
    -0.70
    hews
    -0.69
    ãĥł
    -0.68
    hew
    -0.68
    Ͻ
    -0.66
    POSITIVE LOGITS
     drone
    1.36
     drones
    1.24
     buzzing
    0.96
     Drone
    0.93
     pilots
    0.85
     swarm
    0.84
     unmanned
    0.80
     strike
    0.80
     flying
    0.79
     aircraft
    0.78
    Activations Density 0.012%

    No Known Activations