© 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. 1-RES-JB
    11. 16907
    Prev
    Next
    INDEX
    Explanations

    mentions and descriptions of breakfast items

    oai_token-act-pair · gpt-3.5-turbo

    mentions of breakfast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aft
    -0.75
    andro
    -0.70
    aws
    -0.69
    Engineers
    -0.69
    pmwiki
    -0.65
    Reviewer
    -0.64
    RH
    -0.63
    pg
    -0.63
    LESS
    -0.62
    oping
    -0.62
    POSITIVE LOGITS
     breakfast
    1.35
     mornings
    1.01
     Breakfast
    1.01
     cereal
    0.99
     toast
    0.94
     lunch
    0.94
    halla
    0.92
    eteria
    0.91
     meals
    0.89
     brunch
    0.88
    Activations Density 0.007%

    No Known Activations