© 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. 7-RES-JB
    11. 12690
    Prev
    Next
    INDEX
    Explanations

    references to playing games or participating in interactive experiences

    oai_token-act-pair · gpt-3.5-turbo

    usages of the word "play" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.79
    thening
    -0.78
     Apost
    -0.70
     Beir
    -0.69
    gencies
    -0.69
    pora
    -0.67
     commencement
    -0.66
    plet
    -0.65
    udeau
    -0.62
    ascus
    -0.61
    POSITIVE LOGITS
    testing
    1.17
    tested
    1.17
    ername
    1.14
    GROUND
    1.07
    testers
    1.04
    wright
    1.01
    test
    1.01
    lists
    1.00
    tests
    0.91
    plays
    0.87
    Activations Density 0.041%

    No Known Activations