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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18936
    Prev
    Next
    INDEX
    Explanations

    information about incidents involving casualties

    oai_token-act-pair · gpt-3.5-turbo

    references to casualties and injuries in reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.72
     Transcript
    -0.69
     ¯
    -0.66
     Balanced
    -0.64
     Gutenberg
    -0.63
     Conversation
    -0.63
     Investor
    -0.62
     Grass
    -0.62
     Redd
    -0.61
     stripe
    -0.61
    POSITIVE LOGITS
     injured
    1.59
     killed
    1.44
     wounded
    1.37
     hospitalized
    1.30
     detained
    1.29
     arrested
    1.26
     hurt
    1.19
     harmed
    1.18
     fatalities
    1.17
     murdered
    1.16
    Activations Density 0.132%

    No Known Activations