© 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. 11-RES-JB
    11. 14366
    Prev
    Next
    INDEX
    Explanations

    phrases related to natural disasters, particularly earthquakes

    oai_token-act-pair · gpt-3.5-turbo

    references to earthquakes and related phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atives
    -0.82
    skirts
    -0.80
     Parenthood
    -0.78
    alde
    -0.75
     Purs
    -0.70
    orney
    -0.69
    ket
    -0.69
    idav
    -0.68
    secut
    -0.68
    ublic
    -0.67
    POSITIVE LOGITS
     rupture
    1.01
    hower
    0.92
     magnitude
    0.91
     hazard
    0.87
     earthquake
    0.86
     quake
    0.86
    wave
    0.85
     occurrence
    0.84
     landfall
    0.83
     catastrophe
    0.81
    Activations Density 0.081%

    No Known Activations