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. 0-RES-JB
    6. 17721
    Prev
    Next
    INDEX
    Explanations

    mentions of city names, especially emphasizing 'City' as part of the name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nir
    -0.71
    Downloadha
    -0.64
    milo
    -0.62
     DRM
    -0.61
    hesis
    -0.61
     strap
    -0.61
     pc
    -0.61
    prep
    -0.58
    hig
    -0.58
    ="/
    -0.57
    POSITIVE LOGITS
     City
    3.75
    City
    3.00
     CITY
    2.55
    city
    2.32
     city
    2.18
     Cities
    2.04
     Town
    1.80
     Mayor
    1.68
    Mayor
    1.63
     County
    1.50
    Activations Density 0.025%

    No Known Activations