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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 592
    Prev
    Next
    INDEX
    Explanations

    words related to natural disasters, specifically hurricanes

    oai_token-act-pair · gpt-3.5-turbo

    references to hurricanes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eem
    -1.04
    sie
    -1.02
    shaw
    -1.02
    ington
    -1.00
    sa
    -0.89
    unal
    -0.88
    atum
    -0.85
    skirts
    -0.84
    sem
    -0.84
    stra
    -0.84
    POSITIVE LOGITS
     landfall
    0.86
     hurricane
    0.83
     hurricanes
    0.79
     intensity
    0.77
     hysteria
    0.76
     swarm
    0.73
     tsunami
    0.72
     Hurricanes
    0.71
     blackout
    0.69
     catastrophe
    0.69
    Activations Density 0.024%

    No Known Activations