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. 0-RES-JB
    6. 5744
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'potato'

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of potatoes and beans in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iques
    -0.98
    IGHTS
    -0.87
    speak
    -0.86
    facts
    -0.85
     CDs
    -0.83
     Reps
    -0.83
    casts
    -0.82
    books
    -0.82
    iuses
    -0.81
    aways
    -0.80
    POSITIVE LOGITS
     potato
    2.11
     Potato
    1.82
     vegetable
    1.78
    bean
    1.77
     bean
    1.70
     Bean
    1.65
     strawberry
    1.26
     tomato
    1.24
     mushroom
    1.22
    flower
    1.20
    Activations Density 0.037%

    No Known Activations