© 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. 3-RES-JB
    11. 5329
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive emotions, specifically focusing on happiness

    oai_token-act-pair · gpt-3.5-turbo

    references to happiness and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 3 - joy

    No Comments

    Negative Logits
    sonian
    -0.79
    interstitial
    -0.70
    enegger
    -0.65
    heny
    -0.64
    soDeliveryDate
    -0.63
    arin
    -0.62
    books
    -0.62
     Runner
    -0.61
    DoS
    -0.60
    MpServer
    -0.60
    POSITIVE LOGITS
    fulness
    0.88
     happiness
    0.88
    appiness
    0.86
    owship
    0.80
    ¿½
    0.78
     Pradesh
    0.76
    ful
    0.75
    istic
    0.75
     expectancy
    0.75
    ishment
    0.74
    Activations Density 0.013%

    No Known Activations