© 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. 2-RES-JB
    11. 1518
    Prev
    Next
    INDEX
    Explanations

    mentions of breakfast-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to breakfast

    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
    aws
    -0.69
    aft
    -0.67
     Jericho
    -0.67
     sclerosis
    -0.65
    effic
    -0.64
     Exile
    -0.64
    ne
    -0.62
    abases
    -0.62
    Engineers
    -0.62
    oral
    -0.62
    POSITIVE LOGITS
     breakfast
    1.15
     Breakfast
    0.88
    eteria
    0.87
     cereal
    0.86
     mornings
    0.84
     toast
    0.84
     lunch
    0.81
     buffet
    0.81
     meals
    0.79
    time
    0.78
    Activations Density 0.008%

    No Known Activations