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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 15619
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action against various issues such as climate change, corruption, poverty, and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to combating or tackling significant global issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.88
    ĸļ
    -0.71
     Minutes
    -0.70
     congratulations
    -0.66
    áµ
    -0.64
     announ
    -0.64
     Zup
    -0.63
    ographs
    -0.62
    Base
    -0.61
    ographed
    -0.61
    POSITIVE LOGITS
     homelessness
    1.09
     climate
    1.03
     obesity
    1.03
     poverty
    1.00
     rampant
    0.98
     overcrowd
    0.98
     malnutrition
    0.97
     congestion
    0.94
     alcoholism
    0.93
     deforestation
    0.92
    Activations Density 0.187%

    No Known Activations