© 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. 12468
    Prev
    Next
    INDEX
    Explanations

    instances where someone is asked to be vigilant or watchful

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attentiveness or vigilance

    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
     Aires
    -0.63
     hailed
    -0.62
    Solution
    -0.61
    ZA
    -0.59
     JUSTICE
    -0.59
    otte
    -0.59
     Aren
    -0.59
     nowhere
    -0.58
    IAS
    -0.58
    =>
    -0.58
    POSITIVE LOGITS
     lookout
    1.35
     lid
    1.26
     vigil
    1.08
     eye
    1.04
     diary
    0.97
     tabs
    0.95
     composure
    0.94
     vigilant
    0.90
     wary
    0.88
     journal
    0.87
    Activations Density 0.064%

    No Known Activations