© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 16817
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigns, particularly mentioning Hillary Clinton and Donald Trump

    oai_token-act-pair · gpt-3.5-turbo

    references to political campaigns

    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
     Lumpur
    -0.76
    essional
    -0.75
    ĪĴ
    -0.75
    ipt
    -0.74
    olen
    -0.73
     Alive
    -0.73
    ostic
    -0.69
    Tier
    -0.67
     expire
    -0.66
    ĨĴ
    -0.66
    POSITIVE LOGITS
     campaigns
    1.26
     campaign
    1.08
     manager
    1.01
     slogan
    0.98
    campaign
    0.96
     waged
    0.94
     trail
    0.90
     campaigning
    0.89
    Campaign
    0.89
     slogans
    0.89
    Activations Density 0.029%

    No Known Activations