© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22091
    Prev
    Next
    INDEX
    Explanations

    references to media outlets and sports-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the "USA TODAY" brand name and its associated content

    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
    byn
    -0.79
    PsyNetMessage
    -0.71
     Salman
    -0.63
     whence
    -0.63
    onse
    -0.62
    perse
    -0.61
    76561
    -0.61
    aries
    -0.61
     Gou
    -0.61
    gone
    -0.61
    POSITIVE LOGITS
     NETWORK
    1.45
     Sports
    1.14
     SPORTS
    1.10
     Network
    0.91
    Sports
    0.80
     Sport
    0.75
    icter
    0.73
    Network
    0.70
     College
    0.70
     Entertainment
    0.69
    Activations Density 0.023%

    No Known Activations