© 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. 6-RES-JB
    11. 1474
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent incidents involving casualties

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence and casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.75
     SHOW
    -0.73
     Gleaming
    -0.72
    ãĤ´ãĥ³
    -0.72
     Catalog
    -0.66
     concise
    -0.63
     trillions
    -0.62
     Newsletter
    -0.62
    çļ
    -0.62
    200000
    -0.61
    POSITIVE LOGITS
     wounded
    0.89
     unidentified
    0.85
    endez
    0.85
    nsic
    0.84
     assailants
    0.83
     whom
    0.82
     arrested
    0.81
     wounding
    0.81
     detained
    0.81
     gunman
    0.81
    Activations Density 0.632%

    No Known Activations