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. 11-RES-JB
    6. 15421
    Prev
    Next
    INDEX
    Explanations

    European political figures and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to officials and their roles within the European Union

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chinatown
    -0.98
     Manson
    -0.92
     Arkansas
    -0.90
     Mormon
    -0.89
    awar
    -0.85
     Navajo
    -0.85
     Mormons
    -0.84
     Ranch
    -0.81
     Plains
    -0.79
     Aboriginal
    -0.79
    POSITIVE LOGITS
     Brussels
    1.43
     MEP
    1.41
    EU
    1.40
     EUR
    1.39
    euro
    1.32
     EU
    1.28
     Luxembourg
    1.24
     âĤ¬
    1.24
    Euro
    1.23
     Stras
    1.22
    Activations Density 0.249%

    No Known Activations