© 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. 2-RES-JB
    11. 5378
    Prev
    Next
    INDEX
    Explanations

    words related to the feeling of being anxious or stressed, specifically related to nerves

    oai_token-act-pair · gpt-3.5-turbo

    references to nerves and muscles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alion
    -0.69
    venture
    -0.68
    option
    -0.68
    role
    -0.67
    ctors
    -0.66
    grab
    -0.64
    rama
    -0.63
    lier
    -0.62
    gra
    -0.62
    orig
    -0.62
    POSITIVE LOGITS
     nerves
    1.40
    mith
    0.84
    afety
    0.82
    terness
    0.79
     tiss
    0.78
    ensitive
    0.76
    ourcing
    0.76
    ogyn
    0.73
     inhib
    0.71
    ername
    0.71
    Activations Density 0.013%

    No Known Activations