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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15730
    Prev
    Next
    INDEX
    Explanations

    mentions of drones

    oai_token-act-pair · gpt-3.5-turbo

    references to drones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥł
    -0.83
    orie
    -0.79
    ohyd
    -0.76
     Doyle
    -0.75
    Leader
    -0.74
     Rite
    -0.69
     Sacrament
    -0.67
     Cumber
    -0.66
    OA
    -0.66
     Shore
    -0.66
    POSITIVE LOGITS
     drones
    1.25
     drone
    1.25
     buzzing
    1.08
    dropping
    0.87
     swarm
    0.84
     lapt
    0.83
     Drone
    0.82
     patrolling
    0.80
     circling
    0.79
     unmanned
    0.79
    Activations Density 0.009%

    No Known Activations