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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5235
    Prev
    Next
    INDEX
    Explanations

    references to the geographical location "Ontario"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the region Ontario

    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
    debug
    -0.73
     assassinate
    -0.67
     chars
    -0.64
     cheat
    -0.64
    vel
    -0.64
    asy
    -0.63
     slaves
    -0.62
    mire
    -0.61
    hog
    -0.61
     clot
    -0.61
    POSITIVE LOGITS
     Ontario
    3.68
    Ont
    2.82
     Manitoba
    2.50
     Alberta
    2.49
     Saskatchewan
    2.29
     Quebec
    2.25
     Ont
    2.17
    Toronto
    2.14
     Ottawa
    2.08
     Toronto
    2.05
    Activations Density 0.012%

    No Known Activations