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. 1-RES-JB
    6. 15380
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of meat

    oai_token-act-pair · gpt-3.5-turbo

    references to meat consumption and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Citizens
    -0.74
     Fundamental
    -0.72
    Rated
    -0.68
     Powers
    -0.64
    ordinate
    -0.64
     Hammond
    -0.64
     Morse
    -0.63
    atern
    -0.63
     Nich
    -0.62
    âĸ¬
    -0.62
    POSITIVE LOGITS
    meat
    1.14
     meat
    1.13
    balls
    1.07
     steak
    1.00
     pies
    0.99
     meats
    0.95
     meal
    0.93
    Meat
    0.92
     eater
    0.92
    heads
    0.91
    Activations Density 0.011%

    No Known Activations