© 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. 8-RES-JB
    11. 12948
    Prev
    Next
    INDEX
    Explanations

    words related to "Mck/Mckay" and biographical information, and possibly initiatives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ck" 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     exha
    -0.86
    psons
    -0.79
     impending
    -0.67
     helicop
    -0.66
     livest
    -0.65
    senal
    -0.64
     Palestin
    -0.64
    cipled
    -0.63
    antle
    -0.63
     advers
    -0.62
    POSITIVE LOGITS
    lace
    1.15
    erman
    1.09
    hoff
    1.05
    enstein
    1.04
    etts
    1.03
    crew
    0.99
    enger
    0.98
    enberg
    0.97
    enzie
    0.95
    oning
    0.93
    Activations Density 0.036%

    No Known Activations