© 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. 7-RES-JB
    11. 17239
    Prev
    Next
    INDEX
    Explanations

    mentions of specific law enforcement agencies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police departments and related law enforcement entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.90
    xual
    -0.89
    Downloadha
    -0.86
    opian
    -0.86
    igible
    -0.86
    arget
    -0.79
    å£
    -0.73
    nces
    -0.72
    uces
    -0.68
    ranged
    -0.68
    POSITIVE LOGITS
     Department
    1.28
     Dept
    1.25
     Commissioner
    1.15
     Officers
    1.12
     Constable
    1.07
     Officer
    1.05
     Chief
    1.04
     Enforcement
    0.96
     Bureau
    0.95
     Superintendent
    0.95
    Activations Density 0.050%

    No Known Activations