© 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. 8-RES-JB
    11. 1322
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent incidents or accidents

    oai_token-act-pair · gpt-3.5-turbo

    events involving violence or casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.90
     monopoly
    -0.79
    isSpecialOrderable
    -0.79
     envy
    -0.77
    Ü
    -0.76
     privile
    -0.73
    ãĤ´ãĥ³
    -0.72
     trillions
    -0.72
    Climate
    -0.71
    optim
    -0.70
    POSITIVE LOGITS
     injured
    1.31
     wounded
    1.13
     occupants
    1.10
     suspected
    1.08
     gunman
    1.05
     suspects
    1.04
     victims
    1.03
     eyewitness
    1.02
     arrested
    1.00
     suspect
    0.99
    Activations Density 0.254%

    No Known Activations