© 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. 2-RES-JB
    11. 346
    Prev
    Next
    INDEX
    Explanations

    the word "dessert"

    oai_token-act-pair · gpt-4-turbo

    references to desserts

    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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lev
    -0.84
    inel
    -0.72
     plur
    -0.71
    aird
    -0.71
    orne
    -0.70
    uld
    -0.67
     Hancock
    -0.67
    inventoryQuantity
    -0.66
    uilt
    -0.64
     Vest
    -0.63
    POSITIVE LOGITS
     pudding
    1.13
     dessert
    1.04
    essert
    1.00
     desserts
    0.98
     sweets
    0.84
     Sparkle
    0.84
     cake
    0.83
    oleon
    0.82
    cake
    0.80
    issance
    0.79
    Activations Density 0.014%

    No Known Activations