Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22780
    Prev
    Next
    INDEX
    Explanations

    references to ambulances and emergency services

    oai_token-act-pair · gpt-3.5-turbo

    references to emergency services, particularly ambulances

    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
    estamp
    -0.83
    gemony
    -0.80
     Stronghold
    -0.77
    女
    -0.70
    clud
    -0.69
    heimer
    -0.68
    ularity
    -0.66
    eteenth
    -0.65
     negatives
    -0.63
    aroo
    -0.63
    POSITIVE LOGITS
     paramedics
    1.00
     ambulance
    0.96
     ambul
    0.93
     paramed
    0.91
     responders
    0.84
     evacuation
    0.83
     corps
    0.81
     dispatcher
    0.80
     Corps
    0.78
     evac
    0.78
    Activations Density 0.045%

    No Known Activations