© 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 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. 9936
    Prev
    Next
    INDEX
    Explanations

    relevant tokens related to chemical compounds or medical terminology with the prefix 'yl'

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds that contain the 'yl' suffix

    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
     LAST
    -0.69
     Conquest
    -0.64
     quizz
    -0.62
     Advantage
    -0.62
     Priority
    -0.61
     Struggle
    -0.61
     interests
    -0.60
     pact
    -0.60
    assetsadobe
    -0.59
     enjoyment
    -0.58
    POSITIVE LOGITS
    yl
    4.45
    YL
    2.32
    ylene
    2.11
    yle
    2.06
    ylon
    1.72
    yles
    1.69
    yll
    1.62
    yd
    1.55
    ylan
    1.50
    yr
    1.47
    Activations Density 0.007%

    No Known Activations