© 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. 4-RES-JB
    11. 22297
    Prev
    Next
    INDEX
    Explanations

    keywords related to the action of playing games or activities

    oai_token-act-pair · gpt-3.5-turbo

    instances 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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.82
    pora
    -0.76
    thening
    -0.70
    perial
    -0.70
    ãĤ´ãĥ³
    -0.70
    ewitness
    -0.59
    urst
    -0.59
    intestinal
    -0.58
    Availability
    -0.58
    identally
    -0.57
    POSITIVE LOGITS
    wright
    1.02
    ername
    1.02
    testers
    0.95
    plays
    0.92
    testing
    0.92
    mates
    0.91
    test
    0.89
    cards
    0.86
    tested
    0.83
    otle
    0.79
    Activations Density 0.047%

    No Known Activations