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. 10-RES-JB
    6. 22967
    Prev
    Next
    INDEX
    Explanations

    references to a water crisis related to Flint, Michigan, and the people and events associated with it

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allaah
    -1.08
    Cruz
    -1.04
     Cruz
    -0.98
     Brune
    -0.97
    Dutch
    -0.97
    ø
    -0.93
    ultan
    -0.92
    ijk
    -0.90
     Singapore
    -0.90
     Netherlands
    -0.88
    POSITIVE LOGITS
     Detroit
    1.80
    Detroit
    1.78
     Flint
    1.73
    Michigan
    1.68
     Michigan
    1.64
     Lansing
    1.48
     Wolver
    1.32
     Ruby
    1.32
     ruby
    1.32
     Snyder
    1.31
    Activations Density 0.210%

    No Known Activations