© 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. 1-RES-JB
    11. 20055
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Canadians"

    oai_token-act-pair · gpt-3.5-turbo

    references to Canadians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sk
    -0.71
    fecture
    -0.70
    /+
    -0.68
    sole
    -0.68
    planet
    -0.68
    gur
    -0.67
    ergy
    -0.66
    boss
    -0.64
    ctor
    -0.64
     Verb
    -0.64
    POSITIVE LOGITS
     Canadians
    1.10
    ervatives
    1.03
    ervative
    0.81
    aurus
    0.80
     Australians
    0.79
    umers
    0.78
     Colomb
    0.77
     submar
    0.72
     Jagu
    0.70
    Americans
    0.70
    Activations Density 0.011%

    No Known Activations