© 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 EvalsExportsinterp-engineNEWAPI 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. 9537
    Prev
    Next
    INDEX
    Explanations

    emotions and facial expressions

    oai_token-act-pair · gpt-3.5-turbo

    complex emotional states and reactions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.83
    æ©Ł
    -0.78
     GOODMAN
    -0.77
    etheus
    -0.74
    Ranked
    -0.74
    arthed
    -0.73
    sites
    -0.73
    unes
    -0.73
    ricanes
    -0.70
    CVE
    -0.68
    POSITIVE LOGITS
     laughter
    0.95
     expressions
    0.93
     expression
    0.93
     grin
    0.91
     demeanor
    0.90
     waving
    0.90
     glances
    0.87
     innocence
    0.86
     Expression
    0.84
     stares
    0.83
    Activations Density 0.169%

    No Known Activations