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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3388
    Prev
    Next
    INDEX
    Explanations

    words related to triggers or mechanisms that initiate events or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to triggers, specifically related to actions or events that can initiate a significant reaction or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.81
    apolis
    -0.75
     Partnership
    -0.70
    ¬¼
    -0.69
     Correspond
    -0.68
    aredevil
    -0.67
    sm
    -0.67
    uv
    -0.67
    atography
    -0.67
    hemat
    -0.67
    POSITIVE LOGITS
    trigger
    1.40
     trigger
    1.40
     triggers
    1.28
     triggering
    1.22
     Trigger
    1.02
    Trigger
    0.91
     triggered
    0.87
     warnings
    0.85
    idon
    0.81
     derail
    0.80
    Activations Density 0.008%

    No Known Activations