© 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. 11-RES-JB
    11. 5835
    Prev
    Next
    INDEX
    Explanations

    words related to technology and products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific product names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    worldly
    -0.72
    BuyableInstoreAndOnline
    -0.71
    cean
    -0.71
    poke
    -0.69
    gray
    -0.66
    ¡
    -0.66
    aith
    -0.66
    cum
    -0.66
    yond
    -0.65
    okemon
    -0.65
    POSITIVE LOGITS
     Overview
    1.34
     Basics
    1.32
     Facts
    1.31
     Timeline
    1.25
     Specifications
    1.23
     Uses
    1.17
     Profile
    1.16
     Gets
    1.15
     Highlights
    1.10
     Description
    1.10
    Activations Density 0.380%

    No Known Activations