© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, specifically those related to government or espionage activities

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

    references to the name "Lang."

    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
    hift
    -0.68
    IAL
    -0.67
    ifies
    -0.67
    erate
    -0.66
    ifiable
    -0.64
    inian
    -0.61
    ified
    -0.61
    egal
    -0.59
    itiz
    -0.58
    ials
    -0.58
    POSITIVE LOGITS
    mu
    0.83
    å
    0.66
    anu
    0.63
    bek
    0.63
    fits
    0.62
    ued
    0.62
    glas
    0.62
    knife
    0.60
    lot
    0.59
    try
    0.59
    Activations Density 0.129%

    No Known Activations