© 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. 22231
    Prev
    Next
    INDEX
    Explanations

    references to the city of Toronto

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Toronto

    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
     (=
    -0.76
    ============
    -0.65
    attribute
    -0.65
    CPU
    -0.64
     Faust
    -0.63
    --
    -0.62
     monop
    -0.62
    ={
    -0.62
     Rhod
    -0.61
     invoke
    -0.60
    POSITIVE LOGITS
     Toronto
    3.61
    Toronto
    3.50
     Winnipeg
    2.42
     Montreal
    2.38
     Ottawa
    2.38
     Calgary
    2.37
     Edmonton
    2.35
     Vancouver
    2.32
     Ontario
    2.23
     TTC
    2.09
    Activations Density 0.015%

    No Known Activations