© 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. 3-RES-JB
    11. 23397
    Prev
    Next
    INDEX
    Explanations

    words related to causing distraction or being distracted

    oai_token-act-pair · gpt-3.5-turbo

    terms related to distraction and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iders
    -0.67
    nai
    -0.64
    ITH
    -0.62
    cko
    -0.61
    othermal
    -0.59
     Ibid
    -0.58
     accepted
    -0.57
    ylene
    -0.57
    ibaba
    -0.56
    tain
    -0.56
    POSITIVE LOGITS
     distract
    0.83
     distractions
    0.78
     distraction
    0.77
    wcs
    0.75
    staff
    0.74
    alus
    0.73
    bus
    0.72
     defic
    0.71
    ertation
    0.70
     distracted
    0.69
    Activations Density 0.014%

    No Known Activations