© 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. 3-RES-JB
    11. 12691
    Prev
    Next
    INDEX
    Explanations

    references to dessert items

    oai_token-act-pair · gpt-3.5-turbo

    references to desserts and sweet dishes

    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
     plur
    -0.75
    lev
    -0.72
    ne
    -0.71
    orne
    -0.70
    ought
    -0.70
     Hancock
    -0.70
    sighted
    -0.68
    inel
    -0.68
    uilt
    -0.67
    aird
    -0.64
    POSITIVE LOGITS
     dessert
    1.10
     desserts
    1.05
    essert
    1.03
     pudding
    0.92
    oleon
    0.91
     sweets
    0.87
     Sparkle
    0.84
     topping
    0.84
     cake
    0.81
    mallow
    0.81
    Activations Density 0.011%

    No Known Activations