© 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. 9-RES-JB
    11. 10359
    Prev
    Next
    INDEX
    Explanations

    mentions of emergency services and personnel-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to emergency medical services and first responders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gemony
    -0.80
    rongh
    -0.74
     negatives
    -0.74
    estamp
    -0.73
    fruit
    -0.71
    quote
    -0.68
    atan
    -0.68
    perm
    -0.65
    character
    -0.65
    roth
    -0.64
    POSITIVE LOGITS
     paramed
    1.25
     paramedics
    1.24
     responders
    1.16
     crews
    1.11
     Corps
    1.07
     dispatcher
    1.06
     ambulance
    1.05
     evac
    0.99
     Rescue
    0.98
     rescue
    0.97
    Activations Density 0.122%

    No Known Activations