© 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. 12-RES-JB
    11. 2280
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to royalty or kings

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to the term "King"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ename
    -0.62
     unpaid
    -0.61
    iating
    -0.58
    ted
    -0.58
     proposition
    -0.56
     prompt
    -0.54
     darling
    -0.54
     part
    -0.54
    ATIONS
    -0.53
    orers
    -0.53
    POSITIVE LOGITS
    pin
    1.27
    pins
    1.18
    uin
    1.14
    doms
    1.08
    STON
    1.04
    killer
    0.98
    dom
    0.94
    DOM
    0.94
    ston
    0.94
    maker
    0.92
    Activations Density 0.032%

    No Known Activations