© 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. 11-RES-JB
    11. 20625
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating locations or contexts related to infrastructure projects or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therefore
    -0.64
     furthermore
    -0.63
     moreover
    -0.62
    %:
    -0.61
     besides
    -0.60
    ––
    -0.60
    few
    -0.57
    :(
    -0.57
     whatsoever
    -0.57
     (<
    -0.56
    POSITIVE LOGITS
     Catalonia
    0.84
     Tehran
    0.83
     Nato
    0.83
     Fifa
    0.83
     Nasa
    0.82
     Pyongyang
    0.81
     SpaceX
    0.80
     Sochi
    0.79
     Myanmar
    0.79
     Fukushima
    0.78
    Activations Density 0.674%

    No Known Activations