© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14061
    Prev
    Next
    INDEX
    Explanations

    items on a restaurant menu, particularly focusing on savory dishes like burgers, sausages, appetizers, salads, and various cuisines

    oai_token-act-pair · gpt-3.5-turbo

    various types of food items and menu offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -0.83
    dB
    -0.83
    ayson
    -0.76
    Filename
    -0.73
    invest
    -0.72
    blance
    -0.71
    Dialogue
    -0.71
    ethy
    -0.70
    ETH
    -0.69
    Merit
    -0.69
    POSITIVE LOGITS
     burgers
    1.44
     fries
    1.44
     salads
    1.44
     pancakes
    1.43
     hamb
    1.40
     tacos
    1.38
     steak
    1.37
     pasta
    1.37
     sandwiches
    1.36
     grilled
    1.36
    Activations Density 0.170%

    No Known Activations