© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation or vigilance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "look out."

    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
    TOP
    -0.70
    Own
    -0.66
    Translation
    -0.65
    Problem
    -0.63
    Requ
    -0.62
    bps
    -0.62
    Chel
    -0.62
    tering
    -0.60
    Common
    -0.59
    unch
    -0.58
    POSITIVE LOGITS
    wards
    0.92
    oward
    0.82
     vain
    0.79
     direction
    0.78
    WARD
    0.75
     afar
    0.73
    glass
    0.70
     abyss
    0.70
     directions
    0.69
     sights
    0.69
    Activations Density 0.075%

    No Known Activations