Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23435
    Prev
    Next
    INDEX
    Explanations

    information related to natural disasters, specifically tornadoes

    oai_token-act-pair · gpt-3.5-turbo

    data related to tornado statistics and descriptions

    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
    chwitz
    -0.81
     pee
    -0.74
     creat
    -0.74
     chess
    -0.74
    Priv
    -0.74
     Ashes
    -0.73
    OPLE
    -0.73
    metics
    -0.71
    resso
    -0.70
    Pixel
    -0.70
    POSITIVE LOGITS
     landfall
    1.49
     hurricane
    1.22
     Category
    1.19
     typh
    1.13
     tropical
    1.11
     tornado
    1.11
     Irma
    1.09
    trop
    1.08
     storm
    1.05
     gust
    1.04
    Activations Density 0.214%

    No Known Activations