© 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. 6-RES-JB
    11. 2625
    Prev
    Next
    INDEX
    Explanations

    terms related to catastrophic events or disasters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to catastrophic events and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.71
    VO
    -0.70
    azy
    -0.69
    ateurs
    -0.68
    ogle
    -0.67
     Voc
    -0.66
    guyen
    -0.66
     Expression
    -0.64
    itte
    -0.63
    onsense
    -0.62
    POSITIVE LOGITS
     hurricanes
    1.06
     earthquakes
    1.02
     occurring
    1.00
     disasters
    0.98
     devast
    0.95
     occur
    0.94
     catastrophic
    0.91
     havoc
    0.91
     plague
    0.90
     catast
    0.89
    Activations Density 0.276%

    No Known Activations