© 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. 12493
    Prev
    Next
    INDEX
    Explanations

    terms related to the criminal justice system

    oai_token-act-pair · gpt-3.5-turbo

    references to the criminal justice system and its issues

    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
    -0.93
    Downloadha
    -0.78
    quickShipAvailable
    -0.77
    imus
    -0.73
    below
    -0.72
    é¾įåĸļ士
    -0.71
    rift
    -0.71
    natureconservancy
    -0.70
     toes
    -0.70
    clus
    -0.70
    POSITIVE LOGITS
     homicides
    0.94
     homicide
    0.92
     DEA
    0.89
     Criminal
    0.87
     ATF
    0.86
     punishable
    0.85
     forfeiture
    0.84
     offenses
    0.84
     jurisdiction
    0.83
     crimes
    0.83
    Activations Density 0.228%

    No Known Activations