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. 16491
    Prev
    Next
    INDEX
    Explanations

    references to Hungary or Hungarian

    oai_token-act-pair · gpt-3.5-turbo

    references to Hungary and Hungarian topics

    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
    nesota
    -0.86
    LEASE
    -0.80
    20439
    -0.79
    peer
    -0.79
    bleacher
    -0.74
    grading
    -0.72
    BOOK
    -0.72
    creation
    -0.71
    gradation
    -0.71
    ointed
    -0.71
    POSITIVE LOGITS
    Hung
    1.33
     Budapest
    1.27
     Hungary
    1.21
     Hungarian
    1.07
     Hung
    1.03
     Viktor
    0.98
    awei
    0.87
    oslov
    0.80
     Yug
    0.78
     Yanuk
    0.78
    Activations Density 0.008%

    No Known Activations