© 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. 6-RES-JB
    11. 3020
    Prev
    Next
    INDEX
    Explanations

    smiling or expressions related to happiness and positivity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of happiness or amusement, particularly related to smiling and laughter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 6 - joy

    No Comments

    Negative Logits
     exhibits
    -0.73
     Princ
    -0.72
    NK
    -0.70
     colle
    -0.70
     Activities
    -0.68
     shelves
    -0.68
     Practices
    -0.67
     Rue
    -0.66
     deliberations
    -0.65
     precincts
    -0.65
    POSITIVE LOGITS
    ings
    1.12
    able
    0.98
    athon
    0.97
    iness
    0.91
    idity
    0.89
    eful
    0.89
    iem
    0.88
    ingly
    0.87
    ably
    0.84
     greets
    0.82
    Activations Density 0.168%

    No Known Activations