© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3006
    Prev
    Next
    INDEX
    Explanations

    words related to stripping or scrapping in the context of manufacturing or working with metals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    variations of the word "strip" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     measles
    -0.59
     trust
    -0.57
    ION
    -0.57
     saline
    -0.57
     breakthrough
    -0.56
     AQ
    -0.56
     Annotations
    -0.56
    lain
    -0.55
     theorem
    -0.55
     amd
    -0.54
    POSITIVE LOGITS
    ppers
    1.83
    pper
    1.66
    pping
    1.65
    ppy
    1.62
    pped
    1.61
    ppings
    1.57
    vers
    1.48
    ving
    1.41
    ps
    1.38
    vable
    1.38
    Activations Density 0.074%

    No Known Activations