© 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. 3-RES-JB
    11. 20505
    Prev
    Next
    INDEX
    Explanations

    specific mentions related to aviation incidents or accidents involving Malaysian Airlines Flight MH370

    oai_token-act-pair · gpt-3.5-turbo

    references to specific aircraft incidents and details related to Malaysian Airlines

    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
    女
    -0.97
    galitarian
    -0.79
     Machina
    -0.71
    Regular
    -0.68
    erenn
    -0.67
     Homeless
    -0.66
     Skydragon
    -0.66
    grow
    -0.65
    ãĥ¼ãĥĨ
    -0.65
    Balt
    -0.65
    POSITIVE LOGITS
     airliner
    1.26
    selage
    1.15
     wreckage
    1.13
     hijacked
    1.01
     bombing
    1.01
     detonated
    1.00
     debris
    0.95
     downed
    0.93
     aircraft
    0.93
     deton
    0.89
    Activations Density 0.079%

    No Known Activations