© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20781
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent incidents or accidents involving individuals

    oai_token-act-pair · gpt-3.5-turbo

    actions or events involving explosions or acts of violence

    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
     equivalents
    -0.72
    âĨij
    -0.68
     blah
    -0.66
     anymore
    -0.62
    âĶĢâĶĢâĶĢâĶĢ
    -0.62
     sorted
    -0.62
    =-=-=-=-
    -0.61
     squared
    -0.61
     curated
    -0.60
    equal
    -0.59
    POSITIVE LOGITS
     himself
    1.00
     explosives
    0.87
     fatally
    0.81
    edly
    0.78
    andals
    0.77
     explosive
    0.76
    angering
    0.76
     suicide
    0.75
     rampage
    0.72
     Himself
    0.71
    Activations Density 0.275%

    No Known Activations