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. 3104
    Prev
    Next
    INDEX
    Explanations

    locations and people associated with the state of Colorado

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law enforcement or governmental entities, particularly related to Colorado

    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
     Shinzo
    -1.02
     Africans
    -1.02
     Kenyan
    -1.00
     Ethiop
    -0.97
    Japanese
    -0.95
    Yan
    -0.94
     Yose
    -0.92
    Japan
    -0.91
     Malays
    -0.91
     typh
    -0.91
    POSITIVE LOGITS
     Denver
    2.28
    Denver
    2.21
     Colorado
    2.19
    Colorado
    2.15
     Boulder
    2.06
     Colo
    1.94
     Rockies
    1.62
     Nuggets
    1.59
     Gree
    1.56
     Broncos
    1.54
    Activations Density 0.261%

    No Known Activations