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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 15819
    Prev
    Next
    INDEX
    Explanations

    phrases related to common causes of preventable death and disease, especially in the context of community health

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related issues and their consequences

    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
    wcsstore
    -0.79
     directional
    -0.78
    omorphic
    -0.70
     Dynamic
    -0.70
    oké
    -0.70
    DragonMagazine
    -0.69
    ebus
    -0.69
    livious
    -0.68
     coales
    -0.66
    iband
    -0.65
    POSITIVE LOGITS
     deaths
    1.38
     fatalities
    1.24
     mortality
    1.21
     Deaths
    1.15
     worldwide
    1.09
     epidemic
    1.07
     morbid
    1.02
     homicides
    1.01
     annually
    1.00
     suicides
    0.99
    Activations Density 0.695%

    No Known Activations