© 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. 7-RES-JB
    11. 1575
    Prev
    Next
    INDEX
    Explanations

    mentions of inmates or prison-related activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inmates and the prison system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.79
    NetMessage
    -0.77
    ãĥ¼ãĥ³
    -0.75
    theless
    -0.73
    rous
    -0.72
    adows
    -0.70
    zes
    -0.70
    Tour
    -0.69
    issan
    -0.67
    efully
    -0.67
    POSITIVE LOGITS
    iaries
    0.87
     inmate
    0.82
    iary
    0.81
     inmates
    0.80
     Facility
    0.78
     incarcerated
    0.74
    icts
    0.73
     correctional
    0.69
    arians
    0.67
    ysis
    0.66
    Activations Density 0.059%

    No Known Activations