© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24176
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ke" followed by a single digit number

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ke" and its variations in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     guiActiveUnfocused
    -0.72
    etheless
    -0.70
     IMAGES
    -0.66
     Gateway
    -0.66
    IONS
    -0.62
    resents
    -0.61
    sburgh
    -0.61
    ãĤ¢ãĥ«
    -0.60
    ION
    -0.58
    IBLE
    -0.57
    POSITIVE LOGITS
    aton
    1.08
    ppel
    1.08
    pler
    1.08
    eling
    1.06
    SPA
    1.05
    lder
    1.04
    hma
    1.04
    ptic
    1.01
    ck
    1.01
    ogh
    0.97
    Activations Density 0.030%

    No Known Activations