Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 8201
    Prev
    Next
    INDEX
    Explanations

    mentions of the criminal justice system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the criminal justice system

    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
    yip
    -1.00
    erd
    -0.82
    quickShipAvailable
    -0.80
    rift
    -0.77
    thumbnails
    -0.76
     torches
    -0.74
     curtains
    -0.74
    é¾įåĸļ士
    -0.74
    azy
    -0.73
    together
    -0.73
    POSITIVE LOGITS
     forfeiture
    0.75
     homicide
    0.73
     ATF
    0.73
     DEA
    0.70
     Prosecut
    0.70
     LAW
    0.70
     homicides
    0.68
     prosecution
    0.68
     Aging
    0.68
     jurisdiction
    0.67
    Activations Density 0.186%

    No Known Activations