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. 6-RES-JB
    6. 23551
    Prev
    Next
    INDEX
    Explanations

    food-related words, particularly ingredients and dishes

    oai_token-act-pair · gpt-3.5-turbo

    food-related items and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.79
    Ability
    -0.71
    Jr
    -0.70
    INAL
    -0.69
     Citizens
    -0.67
     Citizen
    -0.66
     Offic
    -0.66
    Dim
    -0.66
    Function
    -0.66
    JM
    -0.65
    POSITIVE LOGITS
    cake
    1.15
     popcorn
    1.05
    bowl
    1.02
     pies
    1.00
     soup
    0.95
    cakes
    0.94
     cake
    0.94
     cakes
    0.90
    meat
    0.90
    wine
    0.90
    Activations Density 0.208%

    No Known Activations