© 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. 10660
    Prev
    Next
    INDEX
    Explanations

    words related to methods and tools used for crowd control and riot management, such as tear gas, rubber bullets, and pepper spray

    oai_token-act-pair · gpt-3.5-turbo

    mentions of crowd control measures used by law enforcement

    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
    comings
    -0.78
    BSD
    -0.73
     Sins
    -0.72
     Transactions
    -0.72
     misunder
    -0.71
    nil
    -0.70
     Seym
    -0.69
    soType
    -0.68
     Wonderland
    -0.67
    fortune
    -0.67
    POSITIVE LOGITS
     grenades
    1.06
     grenade
    0.93
     barric
    0.87
     launchers
    0.85
     checkpoints
    0.79
     tactics
    0.77
     handcuffed
    0.77
    andowski
    0.74
     darts
    0.74
    ansk
    0.74
    Activations Density 0.090%

    No Known Activations