© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 14874
    Prev
    Next
    INDEX
    Explanations

    words related to hurricanes, specifically focusing on the names of hurricanes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific hurricanes

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

    No Comments

    Negative Logits
    skirts
    -1.00
    ifice
    -0.83
    orate
    -0.81
    ells
    -0.81
    unal
    -0.79
    elled
    -0.79
    rown
    -0.78
    buquerque
    -0.75
    haar
    -0.74
    ukes
    -0.73
    POSITIVE LOGITS
     Irma
    1.27
    ricane
    1.26
     Katrina
    1.10
    ricanes
    1.08
     Sandy
    1.02
     Hurricane
    0.98
     Harvey
    0.88
     Relief
    0.87
     Typhoon
    0.87
     storms
    0.83
    Activations Density 0.010%

    No Known Activations