© 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. 1-RES-JB
    11. 5164
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Kos" or "Kul", including variations like "Kosher"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kos" and related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    osterone
    -0.84
    ãĤ¼ãĤ¦ãĤ¹
    -0.78
     Highlander
    -0.67
    skirts
    -0.66
     Oaks
    -0.66
     Lauder
    -0.65
    į
    -0.64
     Reggie
    -0.64
     Females
    -0.63
     Grateful
    -0.62
    POSITIVE LOGITS
     Kos
    1.15
    idon
    1.08
    nown
    1.03
    lyak
    1.00
    kie
    0.97
    cius
    0.94
    utz
    0.92
    ket
    0.91
    ugi
    0.91
    ovan
    0.90
    Activations Density 0.005%

    No Known Activations