© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 24230
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to jails or imprisonment

    oai_token-act-pair · gpt-3.5-turbo

    references to incarceration or jail-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORE
    -0.82
     Bundes
    -0.79
    chell
    -0.67
     Scotia
    -0.62
     Nare
    -0.62
     Myth
    -0.60
     Prosper
    -0.59
    avez
    -0.59
     ITS
    -0.59
    igslist
    -0.58
    POSITIVE LOGITS
     jail
    0.93
     jails
    0.91
    breakers
    0.83
    break
    0.82
    alde
    0.80
     Jail
    0.79
    planet
    0.79
    mallow
    0.78
     imprison
    0.77
    breaking
    0.77
    Activations Density 0.011%

    No Known Activations