© 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. 8-RES-JB
    11. 6435
    Prev
    Next
    INDEX
    Explanations

    information related to medical emergencies and critical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to critical medical conditions and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quotas
    -0.78
    soDeliveryDate
    -0.77
     Dominion
    -0.76
     ãĤµ
    -0.73
     Klux
    -0.71
     DRAGON
    -0.70
     marketers
    -0.70
     Exclusive
    -0.69
    agate
    -0.69
     ECO
    -0.68
    POSITIVE LOGITS
     hospitalized
    1.48
     hospital
    1.47
     healed
    1.37
     injuries
    1.36
     injured
    1.34
     wounds
    1.30
    Doctors
    1.29
     illness
    1.27
     Surgery
    1.27
     patient
    1.27
    Activations Density 0.975%

    No Known Activations