© 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 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. 0-RES-JB
    11. 12542
    Prev
    Next
    INDEX
    Explanations

    related to mental stress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stressed" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proxy
    -0.77
    Magic
    -0.71
     Ghost
    -0.68
    AGE
    -0.65
    race
    -0.65
     torch
    -0.64
    Ghost
    -0.63
    ieve
    -0.61
    mir
    -0.60
    Gate
    -0.60
    POSITIVE LOGITS
     stressed
    3.71
     stressing
    2.17
     stresses
    2.12
     emphasized
    2.04
     stress
    1.90
     Stress
    1.63
     emphas
    1.57
    stress
    1.45
     stressful
    1.35
     reiterated
    1.31
    Activations Density 0.013%

    No Known Activations