© 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. 10-RES-JB
    11. 20591
    Prev
    Next
    INDEX
    Explanations

    phrases related to awards and announcements

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to award announcements and formal recognitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.65
     lately
    -0.61
     Recession
    -0.61
     Shutterstock
    -0.57
    ricanes
    -0.57
     gadgets
    -0.55
    aples
    -0.55
     surprises
    -0.55
    natureconservancy
    -0.54
     stumble
    -0.53
    POSITIVE LOGITS
     accordingly
    0.79
     instead
    0.69
     renamed
    0.68
    .[
    0.67
     indefinitely
    0.66
     anew
    0.65
     permanently
    0.64
    instead
    0.64
     replacement
    0.63
    forth
    0.62
    Activations Density 0.928%

    No Known Activations