© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11362
    Prev
    Next
    INDEX
    Explanations

    details related to aircraft incidents such as crashes and shootdowns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of aircraft incidents and military aviation events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.77
    abis
    -0.69
    enfranch
    -0.66
     Homeless
    -0.65
     landlords
    -0.64
     councillor
    -0.64
    ĸļ
    -0.63
     disenfranch
    -0.62
    Ļ½
    -0.62
     remedies
    -0.62
    POSITIVE LOGITS
     USAF
    1.09
     refuel
    1.09
     airliner
    1.04
     aircraft
    1.00
     airspace
    1.00
     RAF
    1.00
     USS
    0.98
     reconnaissance
    0.94
     orbiting
    0.93
     ashore
    0.93
    Activations Density 0.408%

    No Known Activations