© 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. 6-RES-JB
    11. 7201
    Prev
    Next
    INDEX
    Explanations

    references to corrections, prisons, and prison-related activities or institutions

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to correctional facilities and the corrections 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
    assis
    -0.84
    sonian
    -0.82
    yip
    -0.76
    issan
    -0.75
    peria
    -0.70
    wang
    -0.69
    htar
    -0.69
    wig
    -0.69
    kaya
    -0.68
    dust
    -0.68
    POSITIVE LOGITS
     incarcer
    0.97
     parole
    0.96
     incarceration
    0.91
     correctional
    0.91
     detention
    0.90
     inmates
    0.89
     inmate
    0.89
     Facility
    0.88
     rehabilitation
    0.87
     Detention
    0.87
    Activations Density 0.074%

    No Known Activations