© 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. 2-RES-JB
    11. 8938
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Taipei"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "Taipei" and "Taiwan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.94
    20439
    -0.84
     mileage
    -0.79
    wagen
    -0.74
    д
    -0.70
    nesota
    -0.70
    espie
    -0.70
    NetMessage
    -0.70
     Passenger
    -0.70
    ocene
    -0.70
    POSITIVE LOGITS
    pei
    1.36
    yang
    1.05
     chi
    1.00
    omi
    0.98
    etsu
    0.97
     Dai
    0.95
    ji
    0.92
     Tai
    0.91
    Tai
    0.91
    yu
    0.90
    Activations Density 0.008%

    No Known Activations