© 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. 11-RES-JB
    11. 6763
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement activities such as patrols, crime prevention, and police initiatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to law enforcement and crime prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zot
    -0.85
     Publisher
    -0.82
     UNESCO
    -0.78
    istar
    -0.76
    oslov
    -0.76
    ãĤ´ãĥ³
    -0.74
    Universal
    -0.73
    Sphere
    -0.71
    Cry
    -0.71
    Congratulations
    -0.70
    POSITIVE LOGITS
     arrests
    1.53
     robberies
    1.52
     DUI
    1.45
     crimes
    1.42
     burgl
    1.41
     misdem
    1.40
     suspects
    1.37
     misdemeanor
    1.36
     crime
    1.36
     juveniles
    1.32
    Activations Density 0.521%

    No Known Activations