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. 4374
    Prev
    Next
    INDEX
    Explanations

    words related to political campaigns and demographics

    oai_token-act-pair · gpt-3.5-turbo

    references to key demographics and their political implications

    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
     QC
    -0.81
    itary
    -0.79
    sterdam
    -0.76
     honour
    -0.74
    planet
    -0.72
    EVA
    -0.71
     Cosmetic
    -0.69
     ®
    -0.69
     inspect
    -0.68
     Clockwork
    -0.68
    POSITIVE LOGITS
     Latinos
    1.47
     voters
    1.44
     demographics
    1.44
     turnout
    1.43
     Hispanics
    1.40
    enfranch
    1.37
     voter
    1.37
     Latino
    1.37
     millennials
    1.36
     Millennials
    1.35
    Activations Density 0.642%

    No Known Activations