© 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. 10-RES-JB
    11. 13632
    Prev
    Next
    INDEX
    Explanations

    events or instances of declarations and classifications related to various subjects such as disasters, losses, emergencies, crimes, and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    declarations of emergencies or official statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tales
    -0.79
     glances
    -0.76
     coax
    -0.72
     juxtap
    -0.70
    ierrez
    -0.70
     comparisons
    -0.70
    dding
    -0.68
     spoon
    -0.67
    nings
    -0.66
     glimps
    -0.66
    POSITIVE LOGITS
     unfit
    1.10
    hazard
    1.02
     unsafe
    0.99
     hazardous
    0.95
     unlawful
    0.93
     unconstitutional
    0.91
     ineligible
    0.90
     emergencies
    0.89
    CLASSIFIED
    0.89
    terrorist
    0.87
    Activations Density 0.244%

    No Known Activations