© 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. 0-RES-JB
    11. 6559
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to prisons

    oai_token-act-pair · gpt-3.5-turbo

    references to prisons and jails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uin
    -0.70
    stall
    -0.68
    set
    -0.66
    ainer
    -0.66
     piece
    -0.66
    link
    -0.62
     Item
    -0.59
     brand
    -0.58
     item
    -0.58
     team
    -0.58
    POSITIVE LOGITS
     prisons
    3.64
     jails
    2.92
     prisoners
    1.65
     hospitals
    1.59
     correctional
    1.56
     stadiums
    1.51
     prison
    1.48
     warehouses
    1.48
     inmates
    1.47
     universities
    1.46
    Activations Density 0.012%

    No Known Activations