© 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. 1-RES-JB
    11. 22686
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Toronto

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Toronto

    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
    hardt
    -0.83
    warts
    -0.80
    esson
    -0.77
    sole
    -0.77
    mble
    -0.76
    hol
    -0.75
     Verb
    -0.75
    pn
    -0.73
    hard
    -0.73
    bler
    -0.72
    POSITIVE LOGITS
     Toronto
    1.09
     Raptors
    1.02
     Argon
    0.99
    Toronto
    0.97
     Mississ
    0.93
     Citiz
    0.91
     Harbour
    0.87
     Ottawa
    0.85
     Montreal
    0.84
     Maple
    0.83
    Activations Density 0.011%

    No Known Activations