© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 2956
    Prev
    Next
    INDEX
    Explanations

    terms related to emergency medical services and departments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to emergency medical services and departments

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

    No Comments

    Negative Logits
    alph
    -0.82
    artisan
    -0.76
    âĸ¬âĸ¬
    -0.74
    eters
    -0.70
     Sins
    -0.69
     crooked
    -0.69
    ynt
    -0.68
    xtap
    -0.67
    yg
    -0.66
    aunder
    -0.66
    POSITIVE LOGITS
     evacuation
    0.89
     paramedics
    0.86
     emergency
    0.85
    gencies
    0.85
     evac
    0.83
    monary
    0.82
     resusc
    0.79
     paramed
    0.78
     evacuate
    0.76
    Emergency
    0.74
    Activations Density 0.135%

    No Known Activations