© 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. 11-RES-JB
    11. 12387
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions and communication, particularly involving emotions and physical gestures

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate strong emotions or physical expressions

    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
    arthed
    -0.87
     psychiat
    -0.75
    rules
    -0.69
     Cycle
    -0.68
     Liberties
    -0.64
    é¾įå
    -0.64
     Eucl
    -0.61
    TABLE
    -0.61
    soDeliveryDate
    -0.60
    Lim
    -0.59
    POSITIVE LOGITS
     grin
    1.63
     smile
    1.57
     chuckle
    1.53
     laugh
    1.40
     frown
    1.36
     blush
    1.33
     laughter
    1.30
     sigh
    1.19
     smiles
    1.18
     shrug
    1.17
    Activations Density 0.209%

    No Known Activations