© 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. 11-RES-JB
    11. 17179
    Prev
    Next
    INDEX
    Explanations

    information related to natural disasters and their aftermath

    oai_token-act-pair · gpt-3.5-turbo

    references to natural disasters and their impacts

    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
    arth
    -0.74
    ZI
    -0.69
    ERROR
    -0.68
    ById
    -0.68
    terms
    -0.67
     derog
    -0.67
    uty
    -0.66
    onomy
    -0.64
    got
    -0.64
    ocaust
    -0.64
    POSITIVE LOGITS
     homes
    1.14
     crops
    1.12
     roofs
    1.09
     farmland
    1.07
     villages
    1.05
     roads
    1.02
     farms
    0.99
     livestock
    0.98
     inland
    0.98
     buildings
    0.98
    Activations Density 0.260%

    No Known Activations