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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20503
    Prev
    Next
    INDEX
    Explanations

    mentions of casualties and violent events in news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    counts of casualties, specifically focusing on individuals and demographics within violent events

    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
    ciation
    -0.87
    ãĤ´ãĥ³
    -0.76
    é¾įå¥ij士
    -0.73
    ramid
    -0.72
    pmwiki
    -0.71
    NetMessage
    -0.70
    âķIJâķIJ
    -0.68
    demand
    -0.68
    ________________
    -0.67
    âķIJ
    -0.67
    POSITIVE LOGITS
     juveniles
    1.30
     children
    1.27
     infants
    1.24
     elderly
    1.21
     civilians
    1.20
     minors
    1.20
     teenagers
    1.19
     toddlers
    1.17
     pregnant
    1.12
     policemen
    1.08
    Activations Density 0.213%

    No Known Activations