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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19468
    Prev
    Next
    INDEX
    Explanations

    information about gatherings or protests happening in different locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of group gatherings or protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     successor
    -0.79
     causation
    -0.77
     matured
    -0.75
     reincarn
    -0.75
     Tycoon
    -0.72
    ãĤ´ãĥ³
    -0.72
     immortality
    -0.71
     caus
    -0.71
    inventoryQuantity
    -0.70
     relativity
    -0.69
    POSITIVE LOGITS
     chanting
    1.04
     Occupy
    0.93
     protesting
    0.89
     protesters
    0.89
     riot
    0.89
     barric
    0.87
     marched
    0.86
     protestors
    0.85
     chanted
    0.83
     demonstrators
    0.81
    Activations Density 0.325%

    No Known Activations