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. 15568
    Prev
    Next
    INDEX
    Explanations

    political terms and concepts related to government coalition formations

    oai_token-act-pair · gpt-3.5-turbo

    discussions about political coalitions and their stability

    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
    guyen
    -0.88
    olulu
    -0.84
     Honolulu
    -0.76
     UCS
    -0.75
     honoring
    -0.74
     traveler
    -0.72
     honored
    -0.71
     travelers
    -0.70
    atl
    -0.70
     Hawai
    -0.70
    POSITIVE LOGITS
    Labour
    1.52
     Labour
    1.51
     Tories
    1.47
     Tory
    1.41
     Westminster
    1.36
     Ukip
    1.35
     UKIP
    1.34
     Miliband
    1.34
     Conservatives
    1.32
     Parliament
    1.32
    Activations Density 0.606%

    No Known Activations