© 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 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. 9-RES-JB
    11. 18338
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent actions, especially targeted at prominent figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "assassination" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bos
    -0.85
    orders
    -0.73
    rl
    -0.71
    hist
    -0.70
    ulia
    -0.69
    Commerce
    -0.68
    fm
    -0.67
     Toys
    -0.66
    È
    -0.66
     Seah
    -0.65
    POSITIVE LOGITS
     assassination
    1.00
     assassinated
    0.98
     assass
    0.98
     assassins
    0.97
     assassin
    0.93
     assassinate
    0.90
     Assass
    0.87
     slit
    0.86
     plots
    0.74
     satir
    0.73
    Activations Density 0.078%

    No Known Activations