© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9564
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "sugar."

    oai_token-act-pair · gpt-3.5-turbo

    references to sugar and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.81
    naire
    -0.79
    acular
    -0.78
     FML
    -0.75
    agame
    -0.73
    atche
    -0.73
    ļé
    -0.73
    Downloadha
    -0.71
    ĪĴ
    -0.70
    atform
    -0.70
    POSITIVE LOGITS
     beet
    1.10
     syrup
    1.08
     cane
    1.07
     daddy
    0.86
     sugar
    0.85
    coat
    0.78
     coating
    0.78
     mell
    0.77
    moon
    0.76
    water
    0.76
    Activations Density 0.018%

    No Known Activations