© 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 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. 21505
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of deaths, including overdose deaths, gun deaths, domestic-related deaths, ladder falls, violence-related deaths, and suicides

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fatality and death statistics

    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
    sonian
    -0.94
    ļéĨĴ
    -0.82
    amina
    -0.81
    arity
    -0.75
    tainment
    -0.72
    âķIJ
    -0.70
    ebus
    -0.68
    issance
    -0.65
     manip
    -0.64
    Commerce
    -0.64
    POSITIVE LOGITS
     attributable
    1.13
     occurring
    1.09
     occurred
    1.05
     occur
    1.05
     attributed
    1.02
     Deaths
    1.01
     deaths
    0.98
     involving
    0.98
    icides
    0.96
     aver
    0.95
    Activations Density 0.121%

    No Known Activations