© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15146
    Prev
    Next
    INDEX
    Explanations

    phrases related to stress and stress management

    oai_token-act-pair · gpt-3.5-turbo

    references to stress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izons
    -0.80
    VICE
    -0.76
    ettes
    -0.70
    axies
    -0.66
    HCR
    -0.65
    MET
    -0.65
     smugg
    -0.64
    Aust
    -0.64
    endar
    -0.63
    naissance
    -0.61
    POSITIVE LOGITS
    stress
    0.97
     stress
    0.89
    ors
    0.88
     Stress
    0.86
     reliever
    0.84
    enegger
    0.81
    imaru
    0.79
     cooker
    0.78
    âĶģ
    0.78
    trap
    0.75
    Activations Density 0.011%

    No Known Activations