© 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. 2-RES-JB
    11. 18713
    Prev
    Next
    INDEX
    Explanations

    phrases related to interruptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interrupt" and related forms indicating disruption or interruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.78
    imb
    -0.77
    onz
    -0.72
    venture
    -0.72
    hl
    -0.71
    ":"/
    -0.70
    ports
    -0.70
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.69
    MET
    -0.69
    models
    -0.68
    POSITIVE LOGITS
     interrupt
    1.26
     interrupts
    1.14
     interrupted
    1.06
     interruption
    0.98
    poke
    0.95
    interrupted
    0.94
     answ
    0.85
     pauses
    0.79
    urations
    0.77
     derail
    0.76
    Activations Density 0.006%

    No Known Activations