© 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. 0-RES-JB
    11. 10371
    Prev
    Next
    INDEX
    Explanations

    phrases related to deceased individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to deceased individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Integration
    -0.89
    feature
    -0.68
     tease
    -0.68
    dp
    -0.66
     integration
    -0.62
    pe
    -0.59
    Demand
    -0.58
    bb
    -0.58
     Taste
    -0.58
     trickle
    -0.57
    POSITIVE LOGITS
     deceased
    3.95
     dead
    1.82
     slain
    1.78
     defunct
    1.52
     departed
    1.45
     murdered
    1.42
    dead
    1.36
     extinct
    1.30
     perished
    1.25
     assassinated
    1.23
    Activations Density 0.016%

    No Known Activations