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. 10-RES-JB
    6. 17811
    Prev
    Next
    INDEX
    Explanations

    political terms and phrases related to elections and governing

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative actions and political events related to elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Smithsonian
    -1.05
     ATF
    -0.82
     Yellowstone
    -0.80
     Whitney
    -0.78
     FOIA
    -0.77
     Savannah
    -0.77
    assetsadobe
    -0.76
    olphins
    -0.76
     DOE
    -0.75
    atche
    -0.73
    POSITIVE LOGITS
     parliamentary
    1.55
     electoral
    1.51
     parliament
    1.43
     Elections
    1.43
     elections
    1.41
     centrist
    1.39
     polls
    1.32
     UKIP
    1.31
     MPs
    1.29
    Party
    1.28
    Activations Density 0.600%

    No Known Activations