© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5099
    Prev
    Next
    INDEX
    Explanations

    technical instructions and recommendations related to emergency situations

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases related to emergency procedures and responses

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    galitarian
    -0.80
    olkien
    -0.76
     faire
    -0.72
     royalties
    -0.71
    retty
    -0.71
    roth
    -0.71
    osexual
    -0.71
    ldon
    -0.70
     Playboy
    -0.70
    advertising
    -0.69
    POSITIVE LOGITS
     EMS
    1.78
     paramedics
    1.76
     ambulance
    1.75
     Emergency
    1.73
    Emergency
    1.72
     paramed
    1.70
     emergency
    1.63
     responders
    1.52
     emergencies
    1.50
    EMS
    1.46
    Activations Density 0.426%

    No Known Activations