© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17437
    Prev
    Next
    INDEX
    Explanations

    keywords related to violent and destructive events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate death or tragic 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
    Ku
    -0.69
    ary
    -0.67
    baum
    -0.63
    rane
    -0.62
     priced
    -0.62
    cially
    -0.61
    livious
    -0.61
     Dak
    -0.60
    icans
    -0.58
     Fiction
    -0.57
    POSITIVE LOGITS
     manslaughter
    0.98
     resurrection
    0.92
     wounding
    0.90
     destruction
    0.89
     EMS
    0.89
     rebirth
    0.87
     mayhem
    0.86
     gore
    0.84
     dism
    0.82
     dying
    0.82
    Activations Density 0.134%

    No Known Activations