© 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. 11-RES-JB
    11. 4867
    Prev
    Next
    INDEX
    Explanations

    sentences relating to legal matters or discussing the criminal justice system

    oai_token-act-pair · gpt-3.5-turbo

    discussions about criminal justice and the implications of criminal records on voting rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zinski
    -0.77
     vibration
    -0.73
     Essential
    -0.73
    itage
    -0.70
     Languages
    -0.69
    Brexit
    -0.68
    angular
    -0.68
     Remastered
    -0.67
     divergence
    -0.66
     Improvement
    -0.66
    POSITIVE LOGITS
     prosecuted
    1.65
     jail
    1.64
     convicted
    1.62
     jailed
    1.55
     arrested
    1.54
     incarcerated
    1.53
     sentenced
    1.50
     convict
    1.48
    Prosecutors
    1.45
     criminals
    1.44
    Activations Density 0.539%

    No Known Activations