© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11361
    Prev
    Next
    INDEX
    Explanations

    verbs related to playing or engaging in activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "play" in various forms related to gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thening
    -0.83
     Beir
    -0.73
    ayers
    -0.73
    fty
    -0.69
    ensing
    -0.68
    ewitness
    -0.67
     commencement
    -0.64
     Apost
    -0.61
    gencies
    -0.61
    geries
    -0.61
    POSITIVE LOGITS
    tested
    1.13
    testing
    1.11
    test
    1.04
    ername
    1.04
    wright
    0.98
     games
    0.98
     videog
    0.96
    testers
    0.94
    tests
    0.91
    lists
    0.89
    Activations Density 0.055%

    No Known Activations