© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 5091
    Prev
    Next
    INDEX
    Explanations

    mentions of hurricanes and related terms such as FEMA and Category 1

    oai_token-act-pair · gpt-3.5-turbo

    references to hurricanes and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unal
    -1.01
    pires
    -0.93
    skirts
    -0.86
    atum
    -0.86
    eem
    -0.81
    cius
    -0.80
    ezvous
    -0.79
    susp
    -0.79
    imen
    -0.78
    Republic
    -0.76
    POSITIVE LOGITS
     hurricane
    1.29
     hurricanes
    1.28
    ricane
    1.27
    ricanes
    1.24
     Irma
    1.15
     Katrina
    1.11
     storms
    1.02
     Hurricane
    1.00
     landfall
    0.96
     tornado
    0.93
    Activations Density 0.012%

    No Known Activations