© 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. 11-RES-JB
    11. 12427
    Prev
    Next
    INDEX
    Explanations

    reports of violent incidents with casualties

    oai_token-act-pair · gpt-3.5-turbo

    casualty-related statistics from violent events

    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
     Quarterly
    -0.67
     Exclusive
    -0.66
     ALWAYS
    -0.64
     Kinnikuman
    -0.63
    uctor
    -0.62
     Whenever
    -0.62
    ooth
    -0.61
     occurrence
    -0.61
     Frequency
    -0.60
     Lines
    -0.60
    POSITIVE LOGITS
     wounded
    1.38
     injured
    1.32
     wounding
    1.29
     injuring
    1.21
     injure
    1.09
     inj
    1.00
     critically
    0.93
     injuries
    0.92
     griev
    0.91
     seriously
    0.90
    Activations Density 0.130%

    No Known Activations