© 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. 10682
    Prev
    Next
    INDEX
    Explanations

    words related to projects, such as events, games, movements, projects, films, books, movies, products, shows, songs, albums, tours, recordings, features, genres, speeches, and studies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of media and creative projects

    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
     Qiao
    -0.61
    inez
    -0.60
    NetMessage
    -0.60
     Earthqu
    -0.58
     Levels
    -0.56
     Electricity
    -0.56
     Roads
    -0.55
    suff
    -0.55
    Contents
    -0.55
    Images
    -0.55
    POSITIVE LOGITS
     thats
    0.90
     like
    0.81
     guy
    0.80
     worthy
    0.79
    writer
    0.78
     gimmick
    0.75
     standpoint
    0.74
     theorist
    0.73
    iologist
    0.71
     THAT
    0.70
    Activations Density 0.436%

    No Known Activations