© 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. 0-RES-JB
    11. 1659
    Prev
    Next
    INDEX
    Explanations

    words related to distractions or things that divert attention

    oai_token-act-pair · gpt-3.5-turbo

    references to distractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uth
    -0.75
    EC
    -0.72
     Eth
    -0.70
     eth
    -0.70
     1886
    -0.69
     1918
    -0.68
     1888
    -0.67
    hon
    -0.66
    eta
    -0.66
     Rate
    -0.65
    POSITIVE LOGITS
     distraction
    3.45
     distract
    3.15
     distractions
    3.06
     distracting
    2.90
     distracted
    2.81
     diversion
    1.89
     detract
    1.55
     divert
    1.40
     clutter
    1.31
     diseng
    1.28
    Activations Density 0.025%

    No Known Activations