© 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. 6-RES-JB
    11. 12025
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent actions, particularly involving shootings and killings

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents involving shootings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.78
    heit
    -0.77
     Administ
    -0.76
    soType
    -0.69
    ional
    -0.69
    shire
    -0.68
    Lost
    -0.68
    Trade
    -0.67
     Username
    -0.66
    JV
    -0.66
    POSITIVE LOGITS
     espresso
    0.85
     unarmed
    0.83
    ovie
    0.82
     torped
    0.76
     sparks
    0.74
     blaster
    0.70
     lasers
    0.69
     adrenaline
    0.69
     bullets
    0.69
     penetration
    0.68
    Activations Density 0.165%

    No Known Activations