© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10324
    Prev
    Next
    INDEX
    Explanations

    references to sweet treats or desserts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of desserts

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

    No Comments

    Negative Logits
     Hancock
    -0.75
     plur
    -0.74
     Nau
    -0.71
     Hutchinson
    -0.69
    ne
    -0.68
    inventoryQuantity
    -0.68
    sighted
    -0.67
    orne
    -0.67
    ought
    -0.67
     Caldwell
    -0.66
    POSITIVE LOGITS
    essert
    1.10
     dessert
    1.09
     desserts
    0.97
     Sparkle
    0.91
     sweets
    0.85
    oleon
    0.84
     pudding
    0.81
     decoration
    0.80
     topping
    0.80
    isine
    0.77
    Activations Density 0.015%

    No Known Activations