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

    Neuronpedia

    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. 10-RES-JB
    11. 20682
    Prev
    Next
    INDEX
    Explanations

    mentions of military fighter jets

    oai_token-act-pair · gpt-3.5-turbo

    references to military aircraft, specifically fighter jets

    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
    ask
    -0.75
    ologically
    -0.71
    ologies
    -0.68
     Rowling
    -0.67
    ories
    -0.67
    andre
    -0.66
     NRS
    -0.66
    icone
    -0.65
    imation
    -0.65
    eus
    -0.65
    POSITIVE LOGITS
     jets
    1.29
     jet
    1.23
     pilots
    1.14
     squadron
    1.11
     pilot
    1.03
     Squadron
    1.03
    fighter
    1.02
     fighter
    0.96
     planes
    0.95
    fighters
    0.93
    Activations Density 0.037%

    No Known Activations