© 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. 19992
    Prev
    Next
    INDEX
    Explanations

    references to the food item "toast" and "gravy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of food items, particularly toast

    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
     crossings
    -0.71
    riages
    -0.66
    ologne
    -0.64
    ities
    -0.63
    andro
    -0.62
    chy
    -0.61
    ockey
    -0.61
     drawn
    -0.59
    pent
    -0.58
     Parenthood
    -0.57
    POSITIVE LOGITS
     toast
    1.69
     Toast
    1.53
     antioxid
    0.94
    masters
    0.94
    ï¸
    0.91
     popcorn
    0.86
    cakes
    0.84
    alore
    0.83
    affles
    0.81
     emoji
    0.80
    Activations Density 0.004%

    No Known Activations