© 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. 11-RES-JB
    11. 24428
    Prev
    Next
    INDEX
    Explanations

    phrases related to various emotions, especially sadness and grief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of grief and sorrow

    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
    •layer 11 - sadness

    No Comments

    Negative Logits
    hibition
    -0.81
    iciency
    -0.72
    ushi
    -0.70
    course
    -0.70
    iculty
    -0.68
    giene
    -0.66
    enture
    -0.64
    姫
    -0.63
    tarians
    -0.63
    farious
    -0.62
    POSITIVE LOGITS
     bere
    1.04
     grieving
    1.02
     saddened
    0.97
    felt
    0.94
     stricken
    0.92
    rieved
    0.92
     grief
    0.90
     sorrow
    0.89
     distraught
    0.89
     mourning
    0.89
    Activations Density 0.211%

    No Known Activations