© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16545
    Prev
    Next
    INDEX
    Explanations

    mentions of the city Minneapolis

    oai_token-act-pair · gpt-3.5-turbo
    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
    val
    -0.78
     def
    -0.71
     tiger
    -0.69
    Roman
    -0.68
     mant
    -0.67
     Roman
    -0.66
     hor
    -0.66
    cha
    -0.64
     Tigers
    -0.64
     GC
    -0.64
    POSITIVE LOGITS
     Minneapolis
    3.56
    neapolis
    2.54
     Fargo
    1.62
     Honolulu
    1.57
     Winnipeg
    1.53
    Minnesota
    1.53
     Blooming
    1.52
     Anchorage
    1.52
     Omaha
    1.48
     Newark
    1.42
    Activations Density 0.028%

    No Known Activations