Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21878
    Prev
    Next
    INDEX
    Explanations

    food-related terms, specifically focused on burgers

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "burger" or related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sv
    -0.77
     ast
    -0.76
     Sri
    -0.75
     Circ
    -0.74
     Ach
    -0.72
     SY
    -0.71
     Ae
    -0.70
     Tam
    -0.69
    Az
    -0.68
     Nev
    -0.67
    POSITIVE LOGITS
     burger
    3.51
     burgers
    3.19
     Burger
    3.10
     hamb
    2.48
     fries
    1.97
     steak
    1.92
    urger
    1.65
     taco
    1.62
     tacos
    1.59
     Grill
    1.59
    Activations Density 0.021%

    No Known Activations