© 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. 16108
    Prev
    Next
    INDEX
    Explanations

    mentions of military air operations and equipment

    oai_token-act-pair · gpt-3.5-turbo

    references to air forces and military aviation

    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
     Wem
    -0.69
     Howell
    -0.68
    atown
    -0.68
    aughs
    -0.67
    natureconservancy
    -0.64
     Dickens
    -0.64
     Wong
    -0.64
    ulhu
    -0.63
     Snyder
    -0.62
    ECT
    -0.62
    POSITIVE LOGITS
    lift
    1.21
    ship
    1.16
    ships
    1.13
    liners
    1.08
     superiority
    1.06
    raid
    1.04
     refuel
    1.04
    borne
    1.04
    tight
    1.02
    plane
    1.01
    Activations Density 0.038%

    No Known Activations