© 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 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. 16603
    Prev
    Next
    INDEX
    Explanations

    phrases associated with enjoyment or encouragement

    oai_token-act-pair · gpt-3.5-turbo

    expressions and variations of the word "enjoy."

    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
     scrimmage
    -0.72
     Tycoon
    -0.70
    soDeliveryDate
    -0.70
    orah
    -0.67
    DragonMagazine
    -0.62
    ©¶æ
    -0.62
    ural
    -0.62
    OLOGY
    -0.61
    omo
    -0.61
     mater
    -0.60
    POSITIVE LOGITS
     watching
    1.18
     enjoying
    1.01
     browsing
    0.97
    ably
    0.95
     chatting
    0.93
     owning
    0.90
     listening
    0.90
     playing
    0.89
     seeing
    0.88
     spending
    0.85
    Activations Density 0.064%

    No Known Activations