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

    Neuronpedia

    Jacobian LensNEW
    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. 14891
    Prev
    Next
    INDEX
    Explanations

    statements made by different types of spokespersons, officials, and sources

    oai_token-act-pair · gpt-3.5-turbo

    reported quotes from news agencies and the frequency of statements made by officials

    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
    etsy
    -0.65
     Catalyst
    -0.64
     Wonderland
    -0.62
     Whitney
    -0.62
    Bloom
    -0.62
     Chevy
    -0.61
     Disclosure
    -0.61
     Fellowship
    -0.61
    Board
    -0.59
     Invention
    -0.59
    POSITIVE LOGITS
     AFP
    0.93
     quoting
    0.89
     Kazakh
    0.78
     afterwards
    0.77
     citing
    0.76
     REUTERS
    0.75
     Arabic
    0.75
     Xin
    0.74
     quoted
    0.74
     stressing
    0.73
    Activations Density 0.121%

    No Known Activations