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. 8544
    Prev
    Next
    INDEX
    Explanations

    references to the restaurant chain "Pizza Hut"

    oai_token-act-pair · gpt-3.5-turbo

    references to fast food brands, specifically Pizza Hut and Taco Bell

    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
     Subjects
    -0.83
     fract
    -0.80
     declass
    -0.73
    åĬ
    -0.73
     IPCC
    -0.70
    Filename
    -0.70
     Species
    -0.69
     govern
    -0.68
    vernment
    -0.67
     biod
    -0.67
    POSITIVE LOGITS
     restaurants
    1.07
    ista
    0.99
     Restaur
    0.99
     restaurant
    0.97
     eater
    0.94
     catering
    0.94
     waitress
    0.91
     Stores
    0.90
    becue
    0.89
     cafes
    0.89
    Activations Density 0.201%

    No Known Activations