© 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. 1-RES-JB
    11. 5205
    Prev
    Next
    INDEX
    Explanations

    words ending with the suffix "-ety"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "etiquette" or related social norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raised
    -0.83
    Austral
    -0.77
    PLA
    -0.76
     Redemption
    -0.72
    grave
    -0.68
    enburg
    -0.67
    Footnote
    -0.66
     Interest
    -0.66
    Interstitial
    -0.65
    Room
    -0.64
    POSITIVE LOGITS
    ety
    1.50
    eties
    1.06
    eteen
    1.04
    mology
    0.98
    iencies
    0.84
    ĪĴ
    0.80
    ength
    0.77
     oun
    0.76
    ptoms
    0.75
    izons
    0.75
    Activations Density 0.005%

    No Known Activations