© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 10041
    Prev
    Next
    INDEX
    Explanations

    expressions related to positive emotions through smiling and grinning

    oai_token-act-pair · gpt-3.5-turbo

    expressions of happiness, particularly smiles and grins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BI
    -0.75
    raped
    -0.71
    ctr
    -0.71
    aer
    -0.70
     Administ
    -0.70
    FER
    -0.69
     Mant
    -0.69
    assian
    -0.65
    æ©Ł
    -0.64
    ENCY
    -0.64
    POSITIVE LOGITS
     emot
    1.08
     broadly
    0.92
     goodbye
    0.91
     smile
    0.90
     emoji
    0.89
    ys
    0.88
     radiant
    0.88
     brightly
    0.88
    bows
    0.83
    creen
    0.83
    Activations Density 0.050%

    No Known Activations