© 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. 2397
    Prev
    Next
    INDEX
    Explanations

    details about violent incidents or attacks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to violent incidents and their aftermath

    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
     carrot
    -0.81
    dit
    -0.81
     TTL
    -0.75
     Dry
    -0.74
     Accounting
    -0.72
    \<
    -0.72
     carrots
    -0.72
    redo
    -0.72
     endogenous
    -0.71
     Patent
    -0.71
    POSITIVE LOGITS
     violence
    1.29
     gunman
    1.13
     shootings
    1.10
    ottesville
    1.10
     terrorist
    1.07
    violence
    1.06
     bloodshed
    1.05
     Violence
    1.02
     extremist
    1.02
     rampage
    1.01
    Activations Density 1.140%

    No Known Activations