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. 8-RES-JB
    6. 7525
    Prev
    Next
    INDEX
    Explanations

    cities and locations

    oai_token-act-pair · gpt-3.5-turbo

    city names and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •single token firings
    Individually fires on " Fresno", "Portland", "Denver", "ancouver", "Houston", "Atlanta", ..." Janeiro", ...etc

    No Comments

    Negative Logits
    vana
    -0.81
    renheit
    -0.72
    ilater
    -0.72
    ãĤ½
    -0.69
    schild
    -0.67
     recip
    -0.67
    Enlarge
    -0.64
    arial
    -0.63
    ãĥł
    -0.63
    VALUE
    -0.62
    POSITIVE LOGITS
     City
    0.78
     Zoo
    0.78
     skyline
    0.77
     Region
    0.76
     resident
    0.73
     Township
    0.71
     Rapids
    0.69
     FC
    0.68
     Transit
    0.67
     Heights
    0.67
    Activations Density 0.231%

    No Known Activations