© 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. 1-RES-JB
    11. 6505
    Prev
    Next
    INDEX
    Explanations

    words related to being arrested and sent to jail

    oai_token-act-pair · gpt-3.5-turbo

    references to jails or incarceration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scotia
    -0.67
    FORE
    -0.66
    NetMessage
    -0.66
    Downloadha
    -0.65
    chell
    -0.65
    thodox
    -0.65
     Lynd
    -0.64
    ×ķ
    -0.62
     deaf
    -0.61
     UNESCO
    -0.60
    POSITIVE LOGITS
     Jail
    1.22
     jails
    0.91
    breakers
    0.87
    alde
    0.83
    endas
    0.80
     jail
    0.78
    olla
    0.72
    illo
    0.71
     Cells
    0.69
    Tracker
    0.68
    Activations Density 0.005%

    No Known Activations