© 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. 7-RES-JB
    11. 7960
    Prev
    Next
    INDEX
    Explanations

    natural disaster related words, specifically focusing on earthquake magnitudes

    oai_token-act-pair · gpt-3.5-turbo

    references to earthquake magnitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haw
    -0.74
    nell
    -0.74
    odge
    -0.73
    yrinth
    -0.73
    inelli
    -0.72
    tek
    -0.71
    starter
    -0.71
    nee
    -0.71
    riad
    -0.71
    bies
    -0.70
    POSITIVE LOGITS
     magnitude
    1.16
     scale
    0.81
     è£ıè¦ļéĨĴ
    0.80
     equival
    0.78
     proportions
    0.77
     impact
    0.75
     quake
    0.73
    ricane
    0.73
     caliber
    0.72
    atsu
    0.71
    Activations Density 0.033%

    No Known Activations