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. 3-RES-JB
    6. 2657
    Prev
    Next
    INDEX
    Explanations

    words related to food and nutrition

    oai_token-act-pair · gpt-3.5-turbo

    references to food security and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wink
    -0.75
     Caldwell
    -0.71
     Freem
    -0.70
     Harley
    -0.69
     Rowe
    -0.69
     McKenna
    -0.68
     Knight
    -0.68
    itudinal
    -0.67
    âĸ¬
    -0.67
    20439
    -0.66
    POSITIVE LOGITS
    stuff
    1.05
    borne
    1.03
     eaten
    0.99
    corn
    0.99
    food
    0.92
    cakes
    0.90
     poisoning
    0.89
     additives
    0.89
     tasted
    0.89
     starch
    0.89
    Activations Density 0.030%

    No Known Activations