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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 9220
    Prev
    Next
    INDEX
    Explanations

    ingredients commonly found in food or beverages

    oai_token-act-pair · gpt-3.5-turbo

    food-related ingredients and flavors, particularly fruits and sweeteners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •single token firings
    individually fires on " strawberry", " maple", " peach", " oak", " cherry", and other flavors / fruits

    No Comments

    Negative Logits
    quickShipAvailable
    -0.86
    RAW
    -0.85
     WATCHED
    -0.83
    IGN
    -0.83
    OPER
    -0.81
    Station
    -0.79
    Money
    -0.78
    undo
    -0.77
    andowski
    -0.76
    Offline
    -0.75
    POSITIVE LOGITS
    fruit
    1.08
     bushes
    1.07
     flower
    1.05
     bloss
    1.05
     tree
    1.05
     Blossom
    1.03
     leaf
    1.02
     trees
    1.00
     pine
    1.00
     flowers
    1.00
    Activations Density 0.184%

    No Known Activations