© 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. 17215
    Prev
    Next
    INDEX
    Explanations

    words related to violent events and tragedies

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and tragic events

    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
    itech
    -0.84
    opter
    -0.79
     disadvant
    -0.78
    enture
    -0.76
     incent
    -0.74
    utra
    -0.74
    esty
    -0.73
    Craft
    -0.72
    aurus
    -0.72
    apore
    -0.71
    POSITIVE LOGITS
     eyewitness
    1.07
     gunman
    0.97
     killers
    0.97
     mourn
    0.96
     survivors
    0.94
     perpetrators
    0.94
     PTSD
    0.94
     FEMA
    0.92
     grieving
    0.92
     civilians
    0.91
    Activations Density 1.433%

    No Known Activations