© 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. 2-RES-JB
    11. 1371
    Prev
    Next
    INDEX
    Explanations

    medical emergency-related terms, specifically focusing on CPR and resuscitation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to emergency medical situations and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fruit
    -0.72
    Cra
    -0.71
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
    Square
    -0.69
    seeing
    -0.69
     Crab
    -0.67
     Imperium
    -0.67
    Õ
    -0.67
    posted
    -0.66
     Advertising
    -0.66
    POSITIVE LOGITS
     resusc
    1.41
     CPR
    1.01
     cardiac
    0.99
    ulatory
    0.96
     pac
    0.84
     EMS
    0.84
    esthes
    0.83
     stabilize
    0.83
    ufact
    0.83
    ilitating
    0.81
    Activations Density 0.025%

    No Known Activations